llamaherd/nvidia_model_cache.json at main · gharris012/llamaherd · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
{
  "baai/bge-m3": {
    "fetched_at": 1781000136.4416392,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.764.0\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"DtUy02TGk3ddQGhh92TNbQ==:YjVEg0LAsL4VWyKOQ2DLFcgaAjr+9EgdcuzzjDg6JuzlhG0BJ4LL2dtqYSS0iaWyliZgpA9hiq1O4thfHxTxCvE6WhLNi8GgnTx179YifNBoU2/qaLRg6SCNCN4EATB21hnqrppYGZIIZKIW15Yf0efisO9wTsS+MzMX3dfDUIYn9ETCXVicRUmouXSxasq0\"><meta name=\"readme-version\" content=\"1.0\"><title>baai / bge-m3</title><meta name=\"description\" content=\"Model Overview Description BGE-M3 is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and spars...\" data-rh=\"true\"><meta property=\"og:title\" content=\"baai / bge-m3\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description BGE-M3 is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and spars...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"baai / bge-m3\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description BGE-M3 is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and spars...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=baai%20%2F%20bge-m3&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20BGE-M3%20is%20distinguished%20for%20its%20versatility%20in%20Multi-Functionality%2C%20Multi-Linguality%2C%20and%20Multi-Granularity.%20Multi-Functionality%3A%20It%20can%20simultaneously%20perform%20the%20three%20common%20retrieval%20functionalities%20of%20embedding%20model%3A%20dense%20retrieval%2C%20multi-vector%20retrieval%2C%20and%20spars...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=baai%20%2F%20bge-m3&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20BGE-M3%20is%20distinguished%20for%20its%20versatility%20in%20Multi-Functionality%2C%20Multi-Linguality%2C%20and%20Multi-Granularity.%20Multi-Functionality%3A%20It%20can%20simultaneously%20perform%20the%20three%20common%20retrieval%20functionalities%20of%20embedding%20model%3A%20dense%20retrieval%2C%20multi-vector%20retrieval%2C%20and%20spars...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/baai-bge-m3\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1780673991257\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"https://cdn.readme.io/public/hub/web/Footer.769aa3e9fc194cc963d9.css\">\n<link",
    "source": "https://docs.api.nvidia.com/nim/reference/baai-bge-m3"
  },
  "bytedance/seed-oss-36b-instruct": {
    "fetched_at": 1781000137.0346556,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.764.0\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"AqMyRa25v6cqvMkjzcSSnQ==:JozwgPgDzm+/WiBvVxOQzoHI/9v+xcs2CEIhOawxXZL5ruuqYE6e/4D0rVJq05AC44Rr/bEs+dTTipW0iiFDdmFK9KvGN72pl2ZSdwOYLFeUFByxlqDe0oNxLhnv66G+oeKuARGnwZBIOQPVNo4UFGK7Lc70JHZ4lTyPY/ncnp6s2BXJVTwbMbTWGdbu/px1\"><meta name=\"readme-version\" content=\"1.0\"><title>bytedance / seed-oss-36b-instruct</title><meta name=\"description\" content=\"Seed-OSS-36B-Instruct Description Seed-OSS-36B-Instruct is a 36-billion parameter open-source large language model developed by ByteDance's Seed Team. It is designed for powerful long-context, reasoning, agent and general capabilities, and versatile developer-friendly features. The model features fl...\" data-rh=\"true\"><meta property=\"og:title\" content=\"bytedance / seed-oss-36b-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Seed-OSS-36B-Instruct Description Seed-OSS-36B-Instruct is a 36-billion parameter open-source large language model developed by ByteDance's Seed Team. It is designed for powerful long-context, reasoning, agent and general capabilities, and versatile developer-friendly features. The model features fl...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"bytedance / seed-oss-36b-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Seed-OSS-36B-Instruct Description Seed-OSS-36B-Instruct is a 36-billion parameter open-source large language model developed by ByteDance's Seed Team. It is designed for powerful long-context, reasoning, agent and general capabilities, and versatile developer-friendly features. The model features fl...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=bytedance%20%2F%20seed-oss-36b-instruct&amp;projectTitle=NIM&amp;description=Seed-OSS-36B-Instruct%20Description%20Seed-OSS-36B-Instruct%20is%20a%2036-billion%20parameter%20open-source%20large%20language%20model%20developed%20by%20ByteDance's%20Seed%20Team.%20It%20is%20designed%20for%20powerful%20long-context%2C%20reasoning%2C%20agent%20and%20general%20capabilities%2C%20and%20versatile%20developer-friendly%20features.%20The%20model%20features%20fl...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=bytedance%20%2F%20seed-oss-36b-instruct&amp;projectTitle=NIM&amp;description=Seed-OSS-36B-Instruct%20Description%20Seed-OSS-36B-Instruct%20is%20a%2036-billion%20parameter%20open-source%20large%20language%20model%20developed%20by%20ByteDance's%20Seed%20Team.%20It%20is%20designed%20for%20powerful%20long-context%2C%20reasoning%2C%20agent%20and%20general%20capabilities%2C%20and%20versatile%20developer-friendly%20features.%20The%20model%20features%20fl...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/bytedance-seed-oss-36b-instruct\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1780673991257\"></script><link data-chunk=",
    "source": "https://docs.api.nvidia.com/nim/reference/bytedance-seed-oss-36b-instruct"
  },
  "deepseek-ai/deepseek-v4-flash": {
    "fetched_at": 1779873813.075061,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"RzAYpZNNnf7rEjYv42QPgw==:WhZDs/MZU6y3vwZMwlqeetRpSZHiJGv7O/6u+5B/k+eIXpIaSO0CV4O87h6w9d8/1V+6+BLPU3QePQ/JUP73kCpzHCIZKsi67p2VXluSdzppn+y3rFyMBH0eyKkMvQEH0g5CIR41Nzzi7xofmUrbObeE6DQYsGqchdngmHU/Xb83rcb4k2s/yZSb7MXBYa1z\"><meta name=\"readme-version\" content=\"1.0\"><title>deepseek-ai / deepseek-v4-flash</title><meta name=\"description\" content=\"DeepSeek-V4-Flash Overview Description: DeepSeek-V4-Flash is a Mixture-of-Experts (MoE) language model with 284 billion total parameters and 13 billion activated parameters. DeepSeek-V4-Flash was developed by DeepSeek as a part of DeepSeek-V4 collection. This model is ready for commercial/non-commer...\" data-rh=\"true\"><meta property=\"og:title\" content=\"deepseek-ai / deepseek-v4-flash\" data-rh=\"true\"><meta property=\"og:description\" content=\"DeepSeek-V4-Flash Overview Description: DeepSeek-V4-Flash is a Mixture-of-Experts (MoE) language model with 284 billion total parameters and 13 billion activated parameters. DeepSeek-V4-Flash was developed by DeepSeek as a part of DeepSeek-V4 collection. This model is ready for commercial/non-commer...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"deepseek-ai / deepseek-v4-flash\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"DeepSeek-V4-Flash Overview Description: DeepSeek-V4-Flash is a Mixture-of-Experts (MoE) language model with 284 billion total parameters and 13 billion activated parameters. DeepSeek-V4-Flash was developed by DeepSeek as a part of DeepSeek-V4 collection. This model is ready for commercial/non-commer...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=deepseek-ai%20%2F%20deepseek-v4-flash&amp;projectTitle=NIM&amp;description=DeepSeek-V4-Flash%20Overview%20Description%3A%20DeepSeek-V4-Flash%20is%20a%20Mixture-of-Experts%20(MoE)%20language%20model%20with%20284%20billion%20total%20parameters%20and%2013%20billion%20activated%20parameters.%20DeepSeek-V4-Flash%20was%20developed%20by%20DeepSeek%20as%20a%20part%20of%20DeepSeek-V4%20collection.%20This%20model%20is%20ready%20for%20commercial%2Fnon-commer...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=deepseek-ai%20%2F%20deepseek-v4-flash&amp;projectTitle=NIM&amp;description=DeepSeek-V4-Flash%20Overview%20Description%3A%20DeepSeek-V4-Flash%20is%20a%20Mixture-of-Experts%20(MoE)%20language%20model%20with%20284%20billion%20total%20parameters%20and%2013%20billion%20activated%20parameters.%20DeepSeek-V4-Flash%20was%20developed%20by%20DeepSeek%20as%20a%20part%20of%20DeepSeek-V4%20collection.%20This%20model%20is%20ready%20for%20commercial%2Fnon-commer...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/deepseek-ai-deepseek-v4-flash\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\"",
    "source": "https://docs.api.nvidia.com/nim/reference/deepseek-ai-deepseek-v4-flash"
  },
  "deepseek-ai/deepseek-v4-pro": {
    "fetched_at": 1779873813.3684688,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"2KKvujr4Iz3p7CFamr5S6A==:WgFyNgbFgRwB+KPziOlgtC9GUC//+/tip1AdATztNMV5Tg7gSGG68K05iYMOqTv4Iloe1QrDxqJ4Zn7ozRJiWjsy1OR7iCUqNz9DVyxps835VUSSREHTTftyd2NPO8C7lCkYU/1c0Pih9yNwdesa+q7CDQJoHRIMpGF8v0qNkk6vK4v9ZrMpoY35LHcfAkxK\"><meta name=\"readme-version\" content=\"1.0\"><title>deepseek-ai / deepseek-v4-pro</title><meta name=\"description\" content=\"DeepSeek-V4-Pro Description DeepSeek-V4-Pro is a Mixture-of-Experts (MoE) language model with 1.6 trillion total parameters and 49 billion activated parameters. It features a hybrid attention architecture combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA), achieving 2...\" data-rh=\"true\"><meta property=\"og:title\" content=\"deepseek-ai / deepseek-v4-pro\" data-rh=\"true\"><meta property=\"og:description\" content=\"DeepSeek-V4-Pro Description DeepSeek-V4-Pro is a Mixture-of-Experts (MoE) language model with 1.6 trillion total parameters and 49 billion activated parameters. It features a hybrid attention architecture combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA), achieving 2...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"deepseek-ai / deepseek-v4-pro\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"DeepSeek-V4-Pro Description DeepSeek-V4-Pro is a Mixture-of-Experts (MoE) language model with 1.6 trillion total parameters and 49 billion activated parameters. It features a hybrid attention architecture combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA), achieving 2...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=deepseek-ai%20%2F%20deepseek-v4-pro&amp;projectTitle=NIM&amp;description=DeepSeek-V4-Pro%20Description%20DeepSeek-V4-Pro%20is%20a%20Mixture-of-Experts%20(MoE)%20language%20model%20with%201.6%20trillion%20total%20parameters%20and%2049%20billion%20activated%20parameters.%20It%20features%20a%20hybrid%20attention%20architecture%20combining%20Compressed%20Sparse%20Attention%20(CSA)%20and%20Heavily%20Compressed%20Attention%20(HCA)%2C%20achieving%202...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=deepseek-ai%20%2F%20deepseek-v4-pro&amp;projectTitle=NIM&amp;description=DeepSeek-V4-Pro%20Description%20DeepSeek-V4-Pro%20is%20a%20Mixture-of-Experts%20(MoE)%20language%20model%20with%201.6%20trillion%20total%20parameters%20and%2049%20billion%20activated%20parameters.%20It%20features%20a%20hybrid%20attention%20architecture%20combining%20Compressed%20Sparse%20Attention%20(CSA)%20and%20Heavily%20Compressed%20Attention%20(HCA)%2C%20achieving%202...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/deepseek-ai-deepseek-v4-pro\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" a",
    "source": "https://docs.api.nvidia.com/nim/reference/deepseek-ai-deepseek-v4-pro"
  },
  "google/codegemma-7b": {
    "fetched_at": 1779873814.2507327,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"Hr0/CcG0Ocps0Ev/5fRmkg==:cKO920UwU5lC2qrnnZKN3S/MoQJJRZtzv0K+ZcZGD3ihoOYNLnqtdMBSFP8GtRIfxl8GVEcG78T7THFF98MwwcOu5LwGR1JubRvZTCc5bzM5B+I+kSsKbha5j8jpaIm2eZflc3XZWjePisuak+c+PmRPpbo3OokglizuW5JYd/S5VouRLpbpSQYD58sF3k50\"><meta name=\"readme-version\" content=\"1.0\"><title>google / codegemma-7b</title><meta name=\"description\" content=\"CodeGemma Model card Model Information Model Summary Authors: Google Description CodeGemma is a family of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in...\" data-rh=\"true\"><meta property=\"og:title\" content=\"google / codegemma-7b\" data-rh=\"true\"><meta property=\"og:description\" content=\"CodeGemma Model card Model Information Model Summary Authors: Google Description CodeGemma is a family of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"google / codegemma-7b\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"CodeGemma Model card Model Information Model Summary Authors: Google Description CodeGemma is a family of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20codegemma-7b&amp;projectTitle=NIM&amp;description=CodeGemma%20Model%20card%20Model%20Information%20Model%20Summary%20Authors%3A%20Google%20Description%20CodeGemma%20is%20a%20family%20of%20lightweight%20open%20code%20models%20built%20on%20top%20of%20Gemma.%20CodeGemma%20models%20are%20text-to-text%20and%20text-to-code%20decoder-only%20models%20and%20are%20available%20as%20a%207%20billion%20pretrained%20variant%20that%20specializes%20in...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20codegemma-7b&amp;projectTitle=NIM&amp;description=CodeGemma%20Model%20card%20Model%20Information%20Model%20Summary%20Authors%3A%20Google%20Description%20CodeGemma%20is%20a%20family%20of%20lightweight%20open%20code%20models%20built%20on%20top%20of%20Gemma.%20CodeGemma%20models%20are%20text-to-text%20and%20text-to-code%20decoder-only%20models%20and%20are%20available%20as%20a%207%20billion%20pretrained%20variant%20that%20specializes%20in...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/google-codegemma-7b\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"http",
    "source": "https://docs.api.nvidia.com/nim/reference/google-codegemma-7b"
  },
  "google/gemma-2-2b-it": {
    "fetched_at": 1779873814.3141465,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"/eZQZCAMBsu5hYJicLJAHQ==:9NS0bMHfjhEStx0/87WxjLZ7QTfOfGSjzS8GLScKvFE/3wrctzIAQuQjVa5vxRTJtfmBLxyoAJJUj+7cHA6Pz8BzBB0C31YVpoVqcF8MxPeOrZqltFSK2it8/EeG3hMd+M7Bs6T44U/ZmCmBth30QP73QLHnfBiis4j/E0IYVDO/Yvgi5x34M8hKODTdQ/gi\"><meta name=\"readme-version\" content=\"1.0\"><title>google / gemma-2-2b-it</title><meta name=\"description\" content=\"Gemma 2 Model Card Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-tra...\" data-rh=\"true\"><meta property=\"og:title\" content=\"google / gemma-2-2b-it\" data-rh=\"true\"><meta property=\"og:description\" content=\"Gemma 2 Model Card Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-tra...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"google / gemma-2-2b-it\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Gemma 2 Model Card Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-tra...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-2-2b-it&amp;projectTitle=NIM&amp;description=Gemma%202%20Model%20Card%20Description%20Gemma%20is%20a%20family%20of%20lightweight%2C%20state-of-the-art%20open%20models%20from%20Google%2C%20built%20from%20the%20same%20research%20and%20technology%20used%20to%20create%20the%20Gemini%20models.%20They%20are%20text-to-text%2C%20decoder-only%20large%20language%20models%2C%20available%20in%20English%2C%20with%20open%20weights%20for%20both%20pre-tra...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-2-2b-it&amp;projectTitle=NIM&amp;description=Gemma%202%20Model%20Card%20Description%20Gemma%20is%20a%20family%20of%20lightweight%2C%20state-of-the-art%20open%20models%20from%20Google%2C%20built%20from%20the%20same%20research%20and%20technology%20used%20to%20create%20the%20Gemini%20models.%20They%20are%20text-to-text%2C%20decoder-only%20large%20language%20models%2C%20available%20in%20English%2C%20with%20open%20weights%20for%20both%20pre-tra...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/google-gemma-2-2b-it\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"prel",
    "source": "https://docs.api.nvidia.com/nim/reference/google-gemma-2-2b-it"
  },
  "google/gemma-3-27b-it": {
    "fetched_at": 1777970139.534013,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.709.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"6DPu2PgIsnfumyXQaL9rkQ==:gZ40KfCEQsnQO6KVV7PqIvahhS/NGQ1oXVARs1g6ArIdcGS8W4bqfmdq9Rm8tEF6UHHiyyFvkeR2NxMsXfgW8MhAq7RyrtSnMYnWqPoxZmC913Q/MkavgHcp0hyYPg3ftOnbpe8VU3k7KQlsUrjNvGOteg6y6h0abYQVgAZy0Zgcg7ZDboyMN8b6NqCmAUjg\"><meta name=\"readme-version\" content=\"1.0\"><title>google / gemma-3-27b-it</title><meta name=\"description\" content=\"Gemma 3 model Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-...\" data-rh=\"true\"><meta property=\"og:title\" content=\"google / gemma-3-27b-it\" data-rh=\"true\"><meta property=\"og:description\" content=\"Gemma 3 model Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"google / gemma-3-27b-it\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Gemma 3 model Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-3-27b-it&amp;projectTitle=NIM&amp;description=Gemma%203%20model%20Description%20Gemma%20is%20a%20family%20of%20lightweight%2C%20state-of-the-art%20open%20models%20from%20Google%2C%20built%20from%20the%20same%20research%20and%20technology%20used%20to%20create%20the%20Gemini%20models.%20Gemma%203%20models%20are%20multimodal%2C%20handling%20text%20and%20image%20input%20and%20generating%20text%20output%2C%20with%20open%20weights%20for%20both%20pre-...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-3-27b-it&amp;projectTitle=NIM&amp;description=Gemma%203%20model%20Description%20Gemma%20is%20a%20family%20of%20lightweight%2C%20state-of-the-art%20open%20models%20from%20Google%2C%20built%20from%20the%20same%20research%20and%20technology%20used%20to%20create%20the%20Gemini%20models.%20Gemma%203%20models%20are%20multimodal%2C%20handling%20text%20and%20image%20input%20and%20generating%20text%20output%2C%20with%20open%20weights%20for%20both%20pre-...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/google-gemma-3-27b-it\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1777921742491\"></script><link data-chunk=\"Foo",
    "source": "https://docs.api.nvidia.com/nim/reference/google-gemma-3-27b-it"
  },
  "google/gemma-3n-e2b-it": {
    "fetched_at": 1779873814.4793317,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"mJhH0Ub3IabZaxTlC+8H+A==:mhtSYQJA88A0iUyCFKJ3OKtKScYOTJIpZvEN/d3LeUQNaFX/QaCVRp6BE/cD8wJuLyUKPVDB5xvrFlKXDcKmsIzRDH450YmGxxMSGO5gWCgqLzI/Cg6XbCrMLKEBp9sngU+1j3s1LKklOkJN1FYtePpg11e1OTUAZwuICOdSSYBF9kFGtYH+Uo3N2XjwxtgJ\"><meta name=\"readme-version\" content=\"1.0\"><title>google / gemma-3n-e2b-it</title><meta name=\"description\" content=\"Gemma 3n e2b-it Overview Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal ...\" data-rh=\"true\"><meta property=\"og:title\" content=\"google / gemma-3n-e2b-it\" data-rh=\"true\"><meta property=\"og:description\" content=\"Gemma 3n e2b-it Overview Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal ...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"google / gemma-3n-e2b-it\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Gemma 3n e2b-it Overview Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal ...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-3n-e2b-it&amp;projectTitle=NIM&amp;description=Gemma%203n%20e2b-it%20Overview%20Description%20Gemma%20is%20a%20family%20of%20lightweight%2C%20state-of-the-art%20open%20models%20from%20Google%2C%20built%20from%20the%20same%20research%20and%20technology%20used%20to%20create%20the%20Gemini%20models.%20Gemma%203n%20models%20are%20designed%20for%20efficient%20execution%20on%20low-resource%20devices.%20They%20are%20capable%20of%20multimodal%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-3n-e2b-it&amp;projectTitle=NIM&amp;description=Gemma%203n%20e2b-it%20Overview%20Description%20Gemma%20is%20a%20family%20of%20lightweight%2C%20state-of-the-art%20open%20models%20from%20Google%2C%20built%20from%20the%20same%20research%20and%20technology%20used%20to%20create%20the%20Gemini%20models.%20Gemma%203n%20models%20are%20designed%20for%20efficient%20execution%20on%20low-resource%20devices.%20They%20are%20capable%20of%20multimodal%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/google-gemma-3n-e2b-it\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"",
    "source": "https://docs.api.nvidia.com/nim/reference/google-gemma-3n-e2b-it"
  },
  "google/gemma-3n-e4b-it": {
    "fetched_at": 1779873814.560566,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"2Sau+crj+nY9GfmVFCU2lw==:jbqMZzIvUBiXDPXaMxfiM/2cu0gglZVeCYmR/X8bIDnjYIbA+6t6OYi5RJuvJk9abs5I92XKXZswzE/xjUqUasM+WuMXNCuJbkT5dWo1WGfknFrydYB54n09f1SrvmN7371pw9tcMioxxCTDVROWekqvZZKsh/RmuPWo163FOBSMg2OtnHpOSelcDTHCFCIs\"><meta name=\"readme-version\" content=\"1.0\"><title>google / gemma-3n-e4b-it</title><meta name=\"description\" content=\"Gemma 3n e4b-it Overview Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal ...\" data-rh=\"true\"><meta property=\"og:title\" content=\"google / gemma-3n-e4b-it\" data-rh=\"true\"><meta property=\"og:description\" content=\"Gemma 3n e4b-it Overview Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal ...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"google / gemma-3n-e4b-it\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Gemma 3n e4b-it Overview Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal ...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-3n-e4b-it&amp;projectTitle=NIM&amp;description=Gemma%203n%20e4b-it%20Overview%20Description%20Gemma%20is%20a%20family%20of%20lightweight%2C%20state-of-the-art%20open%20models%20from%20Google%2C%20built%20from%20the%20same%20research%20and%20technology%20used%20to%20create%20the%20Gemini%20models.%20Gemma%203n%20models%20are%20designed%20for%20efficient%20execution%20on%20low-resource%20devices.%20They%20are%20capable%20of%20multimodal%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-3n-e4b-it&amp;projectTitle=NIM&amp;description=Gemma%203n%20e4b-it%20Overview%20Description%20Gemma%20is%20a%20family%20of%20lightweight%2C%20state-of-the-art%20open%20models%20from%20Google%2C%20built%20from%20the%20same%20research%20and%20technology%20used%20to%20create%20the%20Gemini%20models.%20Gemma%203n%20models%20are%20designed%20for%20efficient%20execution%20on%20low-resource%20devices.%20They%20are%20capable%20of%20multimodal%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/google-gemma-3n-e4b-it\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"",
    "source": "https://docs.api.nvidia.com/nim/reference/google-gemma-3n-e4b-it"
  },
  "google/gemma-4-31b-it": {
    "fetched_at": 1779873815.558853,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"wUlTeLIhp/uv4UALCene8Q==:bKi9jPdl8VJpJOeT/LKgmy145ZT5RPdIFnkkQpRgisRERpmPfj5xCfQsvXTOoTS6Ow2Ml+9eOHKR3BPPd1S8utc4yb5OwnTO+nM6uzVV6gX396ETHXtOiXvocDBpqSykU1tle8aNKMHK0HhVIHe3IPDmZWM5DcSQDjq4cPOaM7zdZ7UPcXahLaEI+HG/xr1J\"><meta name=\"readme-version\" content=\"1.0\"><title>google / gemma-4-31b-it</title><meta name=\"description\" content=\"Gemma 4 31B IT Description Gemma 4 31B IT is an open multimodal model built by Google DeepMind that handles text and image inputs, can process video as sequences of frames, and generates text output. It is designed to deliver frontier-level performance for reasoning, agentic workflows, coding, and m...\" data-rh=\"true\"><meta property=\"og:title\" content=\"google / gemma-4-31b-it\" data-rh=\"true\"><meta property=\"og:description\" content=\"Gemma 4 31B IT Description Gemma 4 31B IT is an open multimodal model built by Google DeepMind that handles text and image inputs, can process video as sequences of frames, and generates text output. It is designed to deliver frontier-level performance for reasoning, agentic workflows, coding, and m...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"google / gemma-4-31b-it\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Gemma 4 31B IT Description Gemma 4 31B IT is an open multimodal model built by Google DeepMind that handles text and image inputs, can process video as sequences of frames, and generates text output. It is designed to deliver frontier-level performance for reasoning, agentic workflows, coding, and m...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-4-31b-it&amp;projectTitle=NIM&amp;description=Gemma%204%2031B%20IT%20Description%20Gemma%204%2031B%20IT%20is%20an%20open%20multimodal%20model%20built%20by%20Google%20DeepMind%20that%20handles%20text%20and%20image%20inputs%2C%20can%20process%20video%20as%20sequences%20of%20frames%2C%20and%20generates%20text%20output.%20It%20is%20designed%20to%20deliver%20frontier-level%20performance%20for%20reasoning%2C%20agentic%20workflows%2C%20coding%2C%20and%20m...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=google%20%2F%20gemma-4-31b-it&amp;projectTitle=NIM&amp;description=Gemma%204%2031B%20IT%20Description%20Gemma%204%2031B%20IT%20is%20an%20open%20multimodal%20model%20built%20by%20Google%20DeepMind%20that%20handles%20text%20and%20image%20inputs%2C%20can%20process%20video%20as%20sequences%20of%20frames%2C%20and%20generates%20text%20output.%20It%20is%20designed%20to%20deliver%20frontier-level%20performance%20for%20reasoning%2C%20agentic%20workflows%2C%20coding%2C%20and%20m...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/google-gemma-4-31b-it\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-ch",
    "source": "https://docs.api.nvidia.com/nim/reference/google-gemma-4-31b-it"
  },
  "meta/llama-4-maverick-17b-128e-instruct": {
    "fetched_at": 1779873817.5152886,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"YZhS/dE/XO9o9NoWsrh/jw==:ut8L/DL3c4mj64RDBllBBTNBf8h4B61x3hJcCvoepWx3z5S6ip7mbDzKzWZgd+oWrjEI83aP2moNuIyDUcYuMjqQitjmqEm7JZZHuVQvJWy+xS6crQYJD1CH8uxXWDTksqK7VTh7d5KAvbPPqwA+gej/qzaxdouYYggbhHE4YSmCYyLsj5FNwkuYEjgIA8x4\"><meta name=\"readme-version\" content=\"1.0\"><title>meta / llama-4-maverick-17b-128e-instruct</title><meta name=\"description\" content=\"Model Information The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. These Llama 4 models mark the beginning of ...\" data-rh=\"true\"><meta property=\"og:title\" content=\"meta / llama-4-maverick-17b-128e-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Information The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. These Llama 4 models mark the beginning of ...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"meta / llama-4-maverick-17b-128e-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Information The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. These Llama 4 models mark the beginning of ...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=meta%20%2F%20llama-4-maverick-17b-128e-instruct&amp;projectTitle=NIM&amp;description=Model%20Information%20The%20Llama%204%20collection%20of%20models%20are%20natively%20multimodal%20AI%20models%20that%20enable%20text%20and%20multimodal%20experiences.%20These%20models%20leverage%20a%20mixture-of-experts%20architecture%20to%20offer%20industry-leading%20performance%20in%20text%20and%20image%20understanding.%20These%20Llama%204%20models%20mark%20the%20beginning%20of%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=meta%20%2F%20llama-4-maverick-17b-128e-instruct&amp;projectTitle=NIM&amp;description=Model%20Information%20The%20Llama%204%20collection%20of%20models%20are%20natively%20multimodal%20AI%20models%20that%20enable%20text%20and%20multimodal%20experiences.%20These%20models%20leverage%20a%20mixture-of-experts%20architecture%20to%20offer%20industry-leading%20performance%20in%20text%20and%20image%20understanding.%20These%20Llama%204%20models%20mark%20the%20beginning%20of%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/meta-llama-4-maverick-17b-128e-instruct\"><script src=\"https://cdn.readme.io",
    "source": "https://docs.api.nvidia.com/nim/reference/meta-llama-4-maverick-17b-128e-instruct"
  },
  "meta/llama-guard-4-12b": {
    "fetched_at": 1779873817.445818,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"d3BLEPDqqoK/YMDowsJOOA==:OcS0e3IThXEdobqcydNPjCEwyAx65w6BvgDsPlXn9fHGYMsS6s6EPNrudEu05bxEjxHRc6tKMV5xIN//uqCczhxsg7w01fCeQ5xfeOhnZp66lVOA42Nmym6DoP4EKojRgwbWGzjvNIhGlZPZATCFwYzfVnetzI0/Mu2X6PWj66v7SF4LpdnFijNRffS5wf42\"><meta name=\"readme-version\" content=\"1.0\"><title>meta / llama-guard-4-12b</title><meta name=\"description\" content=\"Llama-Guard-4-12B Overview Description: Llama-Guard-4-12B is a 12-billion parameter, dense, multimodal safety classifier developed by Meta. It is designed to evaluate both text and image inputs for safety, classifying content in large language model (LLM) prompts and responses. The model outputs tex...\" data-rh=\"true\"><meta property=\"og:title\" content=\"meta / llama-guard-4-12b\" data-rh=\"true\"><meta property=\"og:description\" content=\"Llama-Guard-4-12B Overview Description: Llama-Guard-4-12B is a 12-billion parameter, dense, multimodal safety classifier developed by Meta. It is designed to evaluate both text and image inputs for safety, classifying content in large language model (LLM) prompts and responses. The model outputs tex...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"meta / llama-guard-4-12b\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Llama-Guard-4-12B Overview Description: Llama-Guard-4-12B is a 12-billion parameter, dense, multimodal safety classifier developed by Meta. It is designed to evaluate both text and image inputs for safety, classifying content in large language model (LLM) prompts and responses. The model outputs tex...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=meta%20%2F%20llama-guard-4-12b&amp;projectTitle=NIM&amp;description=Llama-Guard-4-12B%20Overview%20Description%3A%20Llama-Guard-4-12B%20is%20a%2012-billion%20parameter%2C%20dense%2C%20multimodal%20safety%20classifier%20developed%20by%20Meta.%20It%20is%20designed%20to%20evaluate%20both%20text%20and%20image%20inputs%20for%20safety%2C%20classifying%20content%20in%20large%20language%20model%20(LLM)%20prompts%20and%20responses.%20The%20model%20outputs%20tex...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=meta%20%2F%20llama-guard-4-12b&amp;projectTitle=NIM&amp;description=Llama-Guard-4-12B%20Overview%20Description%3A%20Llama-Guard-4-12B%20is%20a%2012-billion%20parameter%2C%20dense%2C%20multimodal%20safety%20classifier%20developed%20by%20Meta.%20It%20is%20designed%20to%20evaluate%20both%20text%20and%20image%20inputs%20for%20safety%2C%20classifying%20content%20in%20large%20language%20model%20(LLM)%20prompts%20and%20responses.%20The%20model%20outputs%20tex...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/meta-llama-guard-4-12b\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=",
    "source": "https://docs.api.nvidia.com/nim/reference/meta-llama-guard-4-12b"
  },
  "meta/llama2-70b": {
    "fetched_at": 1779873816.9467106,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"8zJ0EV/ixbdXRWLDZ5cQgg==:VokhKwbp3+UHHX05McPc3JkXVGoCKOCP6+DmGBHlsHebgFXy8+tb6D5V4w6/FPHrim3XrC7MGq3CGzg6MCwG6Cls3dyFpofkXCxu3sHa5TU3lKgEAq5bvvyTQ408/spDtLFBL3fwAiMql01fbyjMwuT4cpjLwJYDXs3sMKdgCJ4NHtXNIM6Ako8h20jUn/x7\"><meta name=\"readme-version\" content=\"1.0\"><title>meta / llama2-70b</title><meta name=\"description\" content=\"Model Overview Description: Llama 2 is a large language AI model comprising a collection of models capable of generating text and code in response to prompts. Third-Party Community Consideration: This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party...\" data-rh=\"true\"><meta property=\"og:title\" content=\"meta / llama2-70b\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description: Llama 2 is a large language AI model comprising a collection of models capable of generating text and code in response to prompts. Third-Party Community Consideration: This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"meta / llama2-70b\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description: Llama 2 is a large language AI model comprising a collection of models capable of generating text and code in response to prompts. Third-Party Community Consideration: This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=meta%20%2F%20llama2-70b&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20Llama%202%20is%20a%20large%20language%20AI%20model%20comprising%20a%20collection%20of%20models%20capable%20of%20generating%20text%20and%20code%20in%20response%20to%20prompts.%20Third-Party%20Community%20Consideration%3A%20This%20model%20is%20not%20owned%20or%20developed%20by%20NVIDIA.%20This%20model%20has%20been%20developed%20and%20built%20to%20a%20third-party...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=meta%20%2F%20llama2-70b&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20Llama%202%20is%20a%20large%20language%20AI%20model%20comprising%20a%20collection%20of%20models%20capable%20of%20generating%20text%20and%20code%20in%20response%20to%20prompts.%20Third-Party%20Community%20Consideration%3A%20This%20model%20is%20not%20owned%20or%20developed%20by%20NVIDIA.%20This%20model%20has%20been%20developed%20and%20built%20to%20a%20third-party...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/meta-llama2-70b\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"https://",
    "source": "https://docs.api.nvidia.com/nim/reference/meta-llama2-70b"
  },
  "microsoft/phi-4-mini-instruct": {
    "fetched_at": 1779873818.5906372,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"XzZe+tei91Jb1/nQWifnYQ==:k4BQCxXIrFn/ovol0RZlcdHq15s+FicAxYfXTsoRX665J503Zwh/SaJQ0bI8+gKm8xHC7kSLjQ7sAFnxjQz4+RxsP6FybRLA/5CiK16cqduKB+HeeKF5uX0DtD27Y4fiTWFi9nFZL8xX2p3xH7HX0fE/2e8QUTCjUrnT5rNVs39tGA2tDmky9IxZv9/22nUP\"><meta name=\"readme-version\" content=\"1.0\"><title>microsoft / phi-4-mini-instruct</title><meta name=\"description\" content=\"Overview Description: Phi-4-Mini is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement...\" data-rh=\"true\"><meta property=\"og:title\" content=\"microsoft / phi-4-mini-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Overview Description: Phi-4-Mini is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"microsoft / phi-4-mini-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Overview Description: Phi-4-Mini is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=microsoft%20%2F%20phi-4-mini-instruct&amp;projectTitle=NIM&amp;description=Overview%20Description%3A%20Phi-4-Mini%20is%20a%20lightweight%20open%20model%20built%20upon%20synthetic%20data%20and%20filtered%20publicly%20available%20websites%20-%20with%20a%20focus%20on%20high-quality%2C%20reasoning%20dense%20data.%20The%20model%20belongs%20to%20the%20Phi-4%20model%20family%20and%20supports%20128K%20token%20context%20length.%20The%20model%20underwent%20an%20enhancement...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=microsoft%20%2F%20phi-4-mini-instruct&amp;projectTitle=NIM&amp;description=Overview%20Description%3A%20Phi-4-Mini%20is%20a%20lightweight%20open%20model%20built%20upon%20synthetic%20data%20and%20filtered%20publicly%20available%20websites%20-%20with%20a%20focus%20on%20high-quality%2C%20reasoning%20dense%20data.%20The%20model%20belongs%20to%20the%20Phi-4%20model%20family%20and%20supports%20128K%20token%20context%20length.%20The%20model%20underwent%20an%20enhancement...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/microsoft-phi-4-mini-instruct\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></",
    "source": "https://docs.api.nvidia.com/nim/reference/microsoft-phi-4-mini-instruct"
  },
  "microsoft/phi-4-multimodal-instruct": {
    "fetched_at": 1779873818.8112617,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"Li/MIpwuYaEukbzGI9Gn7w==:66PX9oFEMRp56lungh+rmYWgupqIjVvbS5hg0YmkIuXumIxy0We647axSFqiAT+tfXb5DUztZ7B65FEO840nsLW9zu29aa+0WosFTIhrc0bMcYGc+27qB6HqKm58siFEyyUiB/EOTLhNY7L/voBlZhNIRUQaWEeNoTuHEp/hiI2MiWieXwCoQuuXv4YXpxoh\"><meta name=\"readme-version\" content=\"1.0\"><title>microsoft / phi-4-multimodal-instruct</title><meta name=\"description\" content=\"Overview Description: Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, generating text outputs, and comes with 128K tok...\" data-rh=\"true\"><meta property=\"og:title\" content=\"microsoft / phi-4-multimodal-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Overview Description: Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, generating text outputs, and comes with 128K tok...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"microsoft / phi-4-multimodal-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Overview Description: Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, generating text outputs, and comes with 128K tok...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=microsoft%20%2F%20phi-4-multimodal-instruct&amp;projectTitle=NIM&amp;description=Overview%20Description%3A%20Phi-4-multimodal-instruct%20is%20a%20lightweight%20open%20multimodal%20foundation%20model%20that%20leverages%20the%20language%2C%20vision%2C%20and%20speech%20research%20and%20datasets%20used%20for%20Phi-3.5%20and%204.0%20models.%20The%20model%20processes%20text%2C%20image%2C%20and%20audio%20inputs%2C%20generating%20text%20outputs%2C%20and%20comes%20with%20128K%20tok...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=microsoft%20%2F%20phi-4-multimodal-instruct&amp;projectTitle=NIM&amp;description=Overview%20Description%3A%20Phi-4-multimodal-instruct%20is%20a%20lightweight%20open%20multimodal%20foundation%20model%20that%20leverages%20the%20language%2C%20vision%2C%20and%20speech%20research%20and%20datasets%20used%20for%20Phi-3.5%20and%204.0%20models.%20The%20model%20processes%20text%2C%20image%2C%20and%20audio%20inputs%2C%20generating%20text%20outputs%2C%20and%20comes%20with%20128K%20tok...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/microsoft-phi-4-multimodal-instruct\"><script src=\"https://cdn.readme.io",
    "source": "https://docs.api.nvidia.com/nim/reference/microsoft-phi-4-multimodal-instruct"
  },
  "minimaxai/minimax-m2.5": {
    "fetched_at": 1777970142.5402508,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.709.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"xWpuxRjnOEms68jgZqn4Pg==:yI7GFIVhFj33VKslQu9Jkd0cJMiSF8k2mOkjR7phvgAPyUn530bAPmzn4Fr6f3S+bksWTEhypHK3rVopi70DSKyIoJTsNKPBPFZ3u2xV7YRoX9GrZWyMeH3p5h7YFjsbghnac2EAAWQy6QT7v08QL2DoKt87F8+zt1usV9kE9qSvb8zN+dPFSnpzbUVwTKA5\"><meta name=\"readme-version\" content=\"1.0\"><title>minimaxai / minimax-m2.5</title><meta name=\"description\" content=\"MiniMax-M2.5 Overview Description: MiniMax-M2.5 is a text generation model trained to perform complex agentic tasks, including software engineering, tool use, search, and office-work style workflows. It is extensively trained with reinforcement learning in hundreds of thousands of complex real-world...\" data-rh=\"true\"><meta property=\"og:title\" content=\"minimaxai / minimax-m2.5\" data-rh=\"true\"><meta property=\"og:description\" content=\"MiniMax-M2.5 Overview Description: MiniMax-M2.5 is a text generation model trained to perform complex agentic tasks, including software engineering, tool use, search, and office-work style workflows. It is extensively trained with reinforcement learning in hundreds of thousands of complex real-world...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"minimaxai / minimax-m2.5\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"MiniMax-M2.5 Overview Description: MiniMax-M2.5 is a text generation model trained to perform complex agentic tasks, including software engineering, tool use, search, and office-work style workflows. It is extensively trained with reinforcement learning in hundreds of thousands of complex real-world...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=minimaxai%20%2F%20minimax-m2.5&amp;projectTitle=NIM&amp;description=MiniMax-M2.5%20Overview%20Description%3A%20MiniMax-M2.5%20is%20a%20text%20generation%20model%20trained%20to%20perform%20complex%20agentic%20tasks%2C%20including%20software%20engineering%2C%20tool%20use%2C%20search%2C%20and%20office-work%20style%20workflows.%20It%20is%20extensively%20trained%20with%20reinforcement%20learning%20in%20hundreds%20of%20thousands%20of%20complex%20real-world...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=minimaxai%20%2F%20minimax-m2.5&amp;projectTitle=NIM&amp;description=MiniMax-M2.5%20Overview%20Description%3A%20MiniMax-M2.5%20is%20a%20text%20generation%20model%20trained%20to%20perform%20complex%20agentic%20tasks%2C%20including%20software%20engineering%2C%20tool%20use%2C%20search%2C%20and%20office-work%20style%20workflows.%20It%20is%20extensively%20trained%20with%20reinforcement%20learning%20in%20hundreds%20of%20thousands%20of%20complex%20real-world...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/minimaxai-minimax-m2.5\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1777921742491\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"sty",
    "source": "https://docs.api.nvidia.com/nim/reference/minimaxai-minimax-m2.5"
  },
  "minimaxai/minimax-m2.7": {
    "fetched_at": 1779873817.7469823,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"sFc8axErHf7MDLVkRcX1Fg==:rLrLFGGXc2wrCuiE1OLlKHZFXnTlTieXziFZQ5/rvPAVphw/Uc/kdyFOp7I7C2UnEUsC6+uC+Lwr4QNu4TiyimgFW6nL6Pe5m8oDtxw3tXjq8ZrlQjFRFS/Qtn8/4dEBuVB0VlvhrBJToQz/mGFjKNbFMRAJz71zGt6Vk88AoYaO4OP3UqmMRMNJLQXPo0UA\"><meta name=\"readme-version\" content=\"1.0\"><title>minimaxai / minimax-m2.7</title><meta name=\"description\" content=\"MiniMax M2.7 Description MiniMax M2.7 is a large language model for complex software engineering, agentic tool use, and office productivity workflows. It is presented as a model deeply participating in its own evolution, with support for complex agent harnesses, dynamic tool search, Agent Teams, and...\" data-rh=\"true\"><meta property=\"og:title\" content=\"minimaxai / minimax-m2.7\" data-rh=\"true\"><meta property=\"og:description\" content=\"MiniMax M2.7 Description MiniMax M2.7 is a large language model for complex software engineering, agentic tool use, and office productivity workflows. It is presented as a model deeply participating in its own evolution, with support for complex agent harnesses, dynamic tool search, Agent Teams, and...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"minimaxai / minimax-m2.7\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"MiniMax M2.7 Description MiniMax M2.7 is a large language model for complex software engineering, agentic tool use, and office productivity workflows. It is presented as a model deeply participating in its own evolution, with support for complex agent harnesses, dynamic tool search, Agent Teams, and...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=minimaxai%20%2F%20minimax-m2.7&amp;projectTitle=NIM&amp;description=MiniMax%20M2.7%20Description%20MiniMax%20M2.7%20is%20a%20large%20language%20model%20for%20complex%20software%20engineering%2C%20agentic%20tool%20use%2C%20and%20office%20productivity%20workflows.%20It%20is%20presented%20as%20a%20model%20deeply%20participating%20in%20its%20own%20evolution%2C%20with%20support%20for%20complex%20agent%20harnesses%2C%20dynamic%20tool%20search%2C%20Agent%20Teams%2C%20and...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=minimaxai%20%2F%20minimax-m2.7&amp;projectTitle=NIM&amp;description=MiniMax%20M2.7%20Description%20MiniMax%20M2.7%20is%20a%20large%20language%20model%20for%20complex%20software%20engineering%2C%20agentic%20tool%20use%2C%20and%20office%20productivity%20workflows.%20It%20is%20presented%20as%20a%20model%20deeply%20participating%20in%20its%20own%20evolution%2C%20with%20support%20for%20complex%20agent%20harnesses%2C%20dynamic%20tool%20search%2C%20Agent%20Teams%2C%20and...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/minimaxai-minimax-m2.7\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"F",
    "source": "https://docs.api.nvidia.com/nim/reference/minimaxai-minimax-m2.7"
  },
  "mistralai/devstral-2-123b-instruct-2512": {
    "fetched_at": 1777970143.0683012,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.709.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"oCUF8nv3WaakM6ewqTBDVw==:mxRDgKlZHlzh1RblsN5HEQgOgcPxJe5I6Z1H6FCU5WYx0SVU9bINygB8yJPhJQojeisCjSGEqLMiU8Vs+6Zk122S+DYrK7BtirPZnlkq1kj37w4HaGkR0V9iv7Bvzuv37uTJQ1IzUBsGBP9M9ApsdPGE4cX7mMWdy5VZajnOGkAMYz3dnEVpiE9podqAGhGg\"><meta name=\"readme-version\" content=\"1.0\"><title>mistralai / devstral-2-123b-instruct-2512</title><meta name=\"description\" content=\"Devstral 2 123B Instruct 2512 Description Devstral 2 123B Instruct 2512 is an agentic large language model designed for software engineering tasks. The model excels at using tools to explore codebases, editing multiple files, and powering software engineering agents, achieving remarkable performance...\" data-rh=\"true\"><meta property=\"og:title\" content=\"mistralai / devstral-2-123b-instruct-2512\" data-rh=\"true\"><meta property=\"og:description\" content=\"Devstral 2 123B Instruct 2512 Description Devstral 2 123B Instruct 2512 is an agentic large language model designed for software engineering tasks. The model excels at using tools to explore codebases, editing multiple files, and powering software engineering agents, achieving remarkable performance...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"mistralai / devstral-2-123b-instruct-2512\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Devstral 2 123B Instruct 2512 Description Devstral 2 123B Instruct 2512 is an agentic large language model designed for software engineering tasks. The model excels at using tools to explore codebases, editing multiple files, and powering software engineering agents, achieving remarkable performance...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20devstral-2-123b-instruct-2512&amp;projectTitle=NIM&amp;description=Devstral%202%20123B%20Instruct%202512%20Description%20Devstral%202%20123B%20Instruct%202512%20is%20an%20agentic%20large%20language%20model%20designed%20for%20software%20engineering%20tasks.%20The%20model%20excels%20at%20using%20tools%20to%20explore%20codebases%2C%20editing%20multiple%20files%2C%20and%20powering%20software%20engineering%20agents%2C%20achieving%20remarkable%20performance...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20devstral-2-123b-instruct-2512&amp;projectTitle=NIM&amp;description=Devstral%202%20123B%20Instruct%202512%20Description%20Devstral%202%20123B%20Instruct%202512%20is%20an%20agentic%20large%20language%20model%20designed%20for%20software%20engineering%20tasks.%20The%20model%20excels%20at%20using%20tools%20to%20explore%20codebases%2C%20editing%20multiple%20files%2C%20and%20powering%20software%20engineering%20agents%2C%20achieving%20remarkable%20performance...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/mistralai-devstral-2-123b-instruct-2512\"><script src=\"https://cdn.r",
    "source": "https://docs.api.nvidia.com/nim/reference/mistralai-devstral-2-123b-instruct-2512"
  },
  "mistralai/magistral-small-2506": {
    "fetched_at": 1777970143.4113271,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.709.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"gb4M7PqDjCtv6NHUX3PxlA==:CAz1zV8ZhV7npgT8v7bo0NlKZLft1WcKb6zOg5cydUh2cLAjCJOb7XqKS9h9Vo5hFMTYAE1JbqWvEBxfIjWPZH/arcuzRQaqa8ytQ8sK37eP8+r0EM0pbyfjHHWbjFCGr+N0EfkrwqalH+20AhcwPyOY9xgpZbGJSj3xUXnKVfB/UiCTTNTqZtk47cC86x8D\"><meta name=\"readme-version\" content=\"1.0\"><title>mistralai / magistral-small-2506</title><meta name=\"description\" content=\"Magistral-Small-2506 Overview Description Magistral-Small-2506 is a lightweight, general-purpose language model that generates and understands natural language for tasks like Q&amp;amp;A, summarization, and instruction following. Designed for efficiency, it balances performance with low computational ov...\" data-rh=\"true\"><meta property=\"og:title\" content=\"mistralai / magistral-small-2506\" data-rh=\"true\"><meta property=\"og:description\" content=\"Magistral-Small-2506 Overview Description Magistral-Small-2506 is a lightweight, general-purpose language model that generates and understands natural language for tasks like Q&amp;amp;A, summarization, and instruction following. Designed for efficiency, it balances performance with low computational ov...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"mistralai / magistral-small-2506\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Magistral-Small-2506 Overview Description Magistral-Small-2506 is a lightweight, general-purpose language model that generates and understands natural language for tasks like Q&amp;amp;A, summarization, and instruction following. Designed for efficiency, it balances performance with low computational ov...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20magistral-small-2506&amp;projectTitle=NIM&amp;description=Magistral-Small-2506%20Overview%20Description%20Magistral-Small-2506%20is%20a%20lightweight%2C%20general-purpose%20language%20model%20that%20generates%20and%20understands%20natural%20language%20for%20tasks%20like%20Q%26amp%3BA%2C%20summarization%2C%20and%20instruction%20following.%20Designed%20for%20efficiency%2C%20it%20balances%20performance%20with%20low%20computational%20ov...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20magistral-small-2506&amp;projectTitle=NIM&amp;description=Magistral-Small-2506%20Overview%20Description%20Magistral-Small-2506%20is%20a%20lightweight%2C%20general-purpose%20language%20model%20that%20generates%20and%20understands%20natural%20language%20for%20tasks%20like%20Q%26amp%3BA%2C%20summarization%2C%20and%20instruction%20following.%20Designed%20for%20efficiency%2C%20it%20balances%20performance%20with%20low%20computational%20ov...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/mistralai-magistral-small-2506\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1777921742491\"></script><li",
    "source": "https://docs.api.nvidia.com/nim/reference/mistralai-magistral-small-2506"
  },
  "mistralai/ministral-14b-instruct-2512": {
    "fetched_at": 1779873818.1652193,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"r1Irq8mPtvArJyKuiZCBjw==:tCG7O7W/l3VWpDiCF5DWPAJ/HwM0rG1W2Lhc2KMGFupTD7jyLArva/jixmhJdY4olHxyE+rsdmIigdqUWWeN69CX0BgqXokQwd3vIEi/2yt7vTm4pTWdf6khmV3BSCaC88gtm8eo8pCF/nsmYIH+b0yfYpM3sWGR4qFZ21gYPsgKdxBujojxaQthjFyB+x0R\"><meta name=\"readme-version\" content=\"1.0\"><title>mistralai / ministral-14b-instruct-2512</title><meta name=\"description\" content=\"Ministral 3 14B Instruct 2512 Description Ministral 3 14B Instruct 2512 FP8 is the largest model in the Ministral 3 family, offering frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities, thi...\" data-rh=\"true\"><meta property=\"og:title\" content=\"mistralai / ministral-14b-instruct-2512\" data-rh=\"true\"><meta property=\"og:description\" content=\"Ministral 3 14B Instruct 2512 Description Ministral 3 14B Instruct 2512 FP8 is the largest model in the Ministral 3 family, offering frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities, thi...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"mistralai / ministral-14b-instruct-2512\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Ministral 3 14B Instruct 2512 Description Ministral 3 14B Instruct 2512 FP8 is the largest model in the Ministral 3 family, offering frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities, thi...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20ministral-14b-instruct-2512&amp;projectTitle=NIM&amp;description=Ministral%203%2014B%20Instruct%202512%20Description%20Ministral%203%2014B%20Instruct%202512%20FP8%20is%20the%20largest%20model%20in%20the%20Ministral%203%20family%2C%20offering%20frontier%20capabilities%20and%20performance%20comparable%20to%20its%20larger%20Mistral%20Small%203.2%2024B%20counterpart.%20A%20powerful%20and%20efficient%20language%20model%20with%20vision%20capabilities%2C%20thi...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20ministral-14b-instruct-2512&amp;projectTitle=NIM&amp;description=Ministral%203%2014B%20Instruct%202512%20Description%20Ministral%203%2014B%20Instruct%202512%20FP8%20is%20the%20largest%20model%20in%20the%20Ministral%203%20family%2C%20offering%20frontier%20capabilities%20and%20performance%20comparable%20to%20its%20larger%20Mistral%20Small%203.2%2024B%20counterpart.%20A%20powerful%20and%20efficient%20language%20model%20with%20vision%20capabilities%2C%20thi...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/mistralai-ministral-14b-instruct-2512\"><script src=\"https://cdn.readm",
    "source": "https://docs.api.nvidia.com/nim/reference/mistralai-ministral-14b-instruct-2512"
  },
  "mistralai/mistral-large-3-675b-instruct-2512": {
    "fetched_at": 1779873819.7048056,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"ZJdPFVi6QKn3THCSsGGftA==:2FwEK8CJLWnTmwHOi9pm29YcSfcpXzeUCuYp+nu9SdbBnxqQUMPJxCdiZ85h+e84w6HmlUJuMjfMhY1lmGK0mbr1v95a/lSwU7Dqz9hjWOWZF6PhMInqt7eQVLGN09ihWcwpIiCrDakkL0lB1XAumFgwRIIowbN+JjBJ/erdvooy6XzEk2RBU7P0g8BXCcjQ\"><meta name=\"readme-version\" content=\"1.0\"><title>mistralai / mistral-large-3-675b-instruct-2512</title><meta name=\"description\" content=\"Mistral Large 3 675B Instruct 2512 Description Mistral Large 3 675B Instruct 2512 is a state-of-the-art general-purpose multimodal granular Mixture-of-Experts model with 41B active parameters and 675B total parameters, trained from the ground up with 3000 H200s. This instruct post-trained version in...\" data-rh=\"true\"><meta property=\"og:title\" content=\"mistralai / mistral-large-3-675b-instruct-2512\" data-rh=\"true\"><meta property=\"og:description\" content=\"Mistral Large 3 675B Instruct 2512 Description Mistral Large 3 675B Instruct 2512 is a state-of-the-art general-purpose multimodal granular Mixture-of-Experts model with 41B active parameters and 675B total parameters, trained from the ground up with 3000 H200s. This instruct post-trained version in...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"mistralai / mistral-large-3-675b-instruct-2512\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Mistral Large 3 675B Instruct 2512 Description Mistral Large 3 675B Instruct 2512 is a state-of-the-art general-purpose multimodal granular Mixture-of-Experts model with 41B active parameters and 675B total parameters, trained from the ground up with 3000 H200s. This instruct post-trained version in...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20mistral-large-3-675b-instruct-2512&amp;projectTitle=NIM&amp;description=Mistral%20Large%203%20675B%20Instruct%202512%20Description%20Mistral%20Large%203%20675B%20Instruct%202512%20is%20a%20state-of-the-art%20general-purpose%20multimodal%20granular%20Mixture-of-Experts%20model%20with%2041B%20active%20parameters%20and%20675B%20total%20parameters%2C%20trained%20from%20the%20ground%20up%20with%203000%20H200s.%20This%20instruct%20post-trained%20version%20in...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20mistral-large-3-675b-instruct-2512&amp;projectTitle=NIM&amp;description=Mistral%20Large%203%20675B%20Instruct%202512%20Description%20Mistral%20Large%203%20675B%20Instruct%202512%20is%20a%20state-of-the-art%20general-purpose%20multimodal%20granular%20Mixture-of-Experts%20model%20with%2041B%20active%20parameters%20and%20675B%20total%20parameters%2C%20trained%20from%20the%20ground%20up%20with%203000%20H200s.%20This%20instruct%20post-trained%20version%20in...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/mistralai-mistral-large-3-675b-instruct-2512\"><scr",
    "source": "https://docs.api.nvidia.com/nim/reference/mistralai-mistral-large-3-675b-instruct-2512"
  },
  "mistralai/mistral-medium-3-instruct": {
    "fetched_at": 1777970144.4401577,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.709.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"zqpabjJMt3gwCOHEQszIvQ==:zVlju4mOOG1b8q+6vduZLTK+VpmJHlpHfTZMZmihg/PXk3r+XBJMWIlIaqUnuJXo9O4jY2YzKEci+Lzm786ouTGdmHNGHk7HE5FwxGfc9RCLEWVM1+hTGHxQgr6j31XlUnZCoHwsT5s1Zbl7wBiH3O2AbSJXkxXNr35/tu4D1qrU0aQrnx+UaofX4+o4/jVZ\"><meta name=\"readme-version\" content=\"1.0\"><title>mistralai / mistral-medium-3-instruct</title><meta name=\"description\" content=\"Mistral Medium 3 Overview Description: Mistral Medium 3 is a frontier-class dense language model optimized for enterprise use. It delivers state-of-the-art performance at significantly lower cost\u2014up to 8\u00d7 cheaper than leading alternatives\u2014while maintaining high usability, adaptability, and deployabi...\" data-rh=\"true\"><meta property=\"og:title\" content=\"mistralai / mistral-medium-3-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Mistral Medium 3 Overview Description: Mistral Medium 3 is a frontier-class dense language model optimized for enterprise use. It delivers state-of-the-art performance at significantly lower cost\u2014up to 8\u00d7 cheaper than leading alternatives\u2014while maintaining high usability, adaptability, and deployabi...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"mistralai / mistral-medium-3-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Mistral Medium 3 Overview Description: Mistral Medium 3 is a frontier-class dense language model optimized for enterprise use. It delivers state-of-the-art performance at significantly lower cost\u2014up to 8\u00d7 cheaper than leading alternatives\u2014while maintaining high usability, adaptability, and deployabi...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20mistral-medium-3-instruct&amp;projectTitle=NIM&amp;description=Mistral%20Medium%203%20Overview%20Description%3A%20Mistral%20Medium%203%20is%20a%20frontier-class%20dense%20language%20model%20optimized%20for%20enterprise%20use.%20It%20delivers%20state-of-the-art%20performance%20at%20significantly%20lower%20cost%E2%80%94up%20to%208%C3%97%20cheaper%20than%20leading%20alternatives%E2%80%94while%20maintaining%20high%20usability%2C%20adaptability%2C%20and%20deployabi...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20mistral-medium-3-instruct&amp;projectTitle=NIM&amp;description=Mistral%20Medium%203%20Overview%20Description%3A%20Mistral%20Medium%203%20is%20a%20frontier-class%20dense%20language%20model%20optimized%20for%20enterprise%20use.%20It%20delivers%20state-of-the-art%20performance%20at%20significantly%20lower%20cost%E2%80%94up%20to%208%C3%97%20cheaper%20than%20leading%20alternatives%E2%80%94while%20maintaining%20high%20usability%2C%20adaptability%2C%20and%20deployabi...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/mistralai-mistral-medium-3-instruct\"><script src=\"https://cdn",
    "source": "https://docs.api.nvidia.com/nim/reference/mistralai-mistral-medium-3-instruct"
  },
  "mistralai/mistral-nemotron": {
    "fetched_at": 1779873819.9023426,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"xsToJtgAeREARrj1Ai7EiA==:nIAlTlypm2FawXHV9hD1By6nvgUJo5j79PXtZgBlp53XCClR5hxdC+Rxrr+YmoayXqUHQMNK1qFaBqkJlnKbxdd1ZMF4JehiaZYfeCKuoUvNemwwdQ/xN9Loht8uouWra+Z+LFa8ThlMKamCDMbIUlfuWkzw109PDQARaM1k7IlFrZhMrRfRj9++JUo5cQ3I\"><meta name=\"readme-version\" content=\"1.0\"><title>mistralai / mistral-nemotron</title><meta name=\"description\" content=\"Mistral-Nemotron Overview Description: Mistral-Nemotron is a large language model produced by Mistral and optimised by NVIDIA that generates human-like text and can be used for a variety of natural language processing tasks, such as text generation, language translation, and text summarization. It i...\" data-rh=\"true\"><meta property=\"og:title\" content=\"mistralai / mistral-nemotron\" data-rh=\"true\"><meta property=\"og:description\" content=\"Mistral-Nemotron Overview Description: Mistral-Nemotron is a large language model produced by Mistral and optimised by NVIDIA that generates human-like text and can be used for a variety of natural language processing tasks, such as text generation, language translation, and text summarization. It i...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"mistralai / mistral-nemotron\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Mistral-Nemotron Overview Description: Mistral-Nemotron is a large language model produced by Mistral and optimised by NVIDIA that generates human-like text and can be used for a variety of natural language processing tasks, such as text generation, language translation, and text summarization. It i...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20mistral-nemotron&amp;projectTitle=NIM&amp;description=Mistral-Nemotron%20Overview%20Description%3A%20Mistral-Nemotron%20is%20a%20large%20language%20model%20produced%20by%20Mistral%20and%20optimised%20by%20NVIDIA%20that%20generates%20human-like%20text%20and%20can%20be%20used%20for%20a%20variety%20of%20natural%20language%20processing%20tasks%2C%20such%20as%20text%20generation%2C%20language%20translation%2C%20and%20text%20summarization.%20It%20i...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20mistral-nemotron&amp;projectTitle=NIM&amp;description=Mistral-Nemotron%20Overview%20Description%3A%20Mistral-Nemotron%20is%20a%20large%20language%20model%20produced%20by%20Mistral%20and%20optimised%20by%20NVIDIA%20that%20generates%20human-like%20text%20and%20can%20be%20used%20for%20a%20variety%20of%20natural%20language%20processing%20tasks%2C%20such%20as%20text%20generation%2C%20language%20translation%2C%20and%20text%20summarization.%20It%20i...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/mistralai-mistral-nemotron\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-",
    "source": "https://docs.api.nvidia.com/nim/reference/mistralai-mistral-nemotron"
  },
  "mistralai/mistral-small-4-119b-2603": {
    "fetched_at": 1779873819.3503275,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"i2lbZSqLnG1YdX+v4xlReQ==:WAx+IG92ltd7cjI0JOffenegW/Neje+R5FOta0KB3MaK3VIRR5kLarIWDlhAAxhq6MyPXAfhSGl9bbH/hujkzAyGVnlxn8OhNsPEOCXUyhNTsrLnXe/9MEgwH/vsdWW54T6TlpJ/2811ebQ2pur0EzwHcQSe2MvHTlrdUd7pFUEUma3Hd18JFW9rg1PxU4oK\"><meta name=\"readme-version\" content=\"1.0\"><title>mistralai / mistral-small-4-119b-2603</title><meta name=\"description\" content=\"Mistral Small 4 119B A6B Description Mistral Small 4 is a powerful hybrid model capable of acting as both a general instruction model and a reasoning model. It unifies the capabilities of three different model families\u2014 Instruct , Reasoning (previously called Magistral), and Devstral \u2014into a single,...\" data-rh=\"true\"><meta property=\"og:title\" content=\"mistralai / mistral-small-4-119b-2603\" data-rh=\"true\"><meta property=\"og:description\" content=\"Mistral Small 4 119B A6B Description Mistral Small 4 is a powerful hybrid model capable of acting as both a general instruction model and a reasoning model. It unifies the capabilities of three different model families\u2014 Instruct , Reasoning (previously called Magistral), and Devstral \u2014into a single,...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"mistralai / mistral-small-4-119b-2603\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Mistral Small 4 119B A6B Description Mistral Small 4 is a powerful hybrid model capable of acting as both a general instruction model and a reasoning model. It unifies the capabilities of three different model families\u2014 Instruct , Reasoning (previously called Magistral), and Devstral \u2014into a single,...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20mistral-small-4-119b-2603&amp;projectTitle=NIM&amp;description=Mistral%20Small%204%20119B%20A6B%20Description%20Mistral%20Small%204%20is%20a%20powerful%20hybrid%20model%20capable%20of%20acting%20as%20both%20a%20general%20instruction%20model%20and%20a%20reasoning%20model.%20It%20unifies%20the%20capabilities%20of%20three%20different%20model%20families%E2%80%94%20Instruct%20%2C%20Reasoning%20(previously%20called%20Magistral)%2C%20and%20Devstral%20%E2%80%94into%20a%20single%2C...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=mistralai%20%2F%20mistral-small-4-119b-2603&amp;projectTitle=NIM&amp;description=Mistral%20Small%204%20119B%20A6B%20Description%20Mistral%20Small%204%20is%20a%20powerful%20hybrid%20model%20capable%20of%20acting%20as%20both%20a%20general%20instruction%20model%20and%20a%20reasoning%20model.%20It%20unifies%20the%20capabilities%20of%20three%20different%20model%20families%E2%80%94%20Instruct%20%2C%20Reasoning%20(previously%20called%20Magistral)%2C%20and%20Devstral%20%E2%80%94into%20a%20single%2C...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/mistralai-mistral-small-4-119b-2603",
    "source": "https://docs.api.nvidia.com/nim/reference/mistralai-mistral-small-4-119b-2603"
  },
  "moonshotai/kimi-k2-instruct": {
    "fetched_at": 1777970144.8354046,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.709.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"FC+Y3pPS5BlAAXEp2P44lg==:KZ0JOjaIWdvETckp2+q3hTdVTt4GuWC6Uk6tNY6bztD5FS0vL1KRRAUIdO2H8cIeWxy5tyUp9b/ycUOgk2Yz86NauEnFZDI1qPtt7imiJU6YNp7DFEd4Wxqt0TKix9RWQoO+my9ygUGMqh56BeLhS7yGh6J5t2+9Eu25jkI71IY6RTxRT7FbsmEN0rkIFOJ/\"><meta name=\"readme-version\" content=\"1.0\"><title>moonshotai / kimi-k2-instruct</title><meta name=\"description\" content=\"Kimi-K2-Instruct Description Kimi K2 Instruct is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding...\" data-rh=\"true\"><meta property=\"og:title\" content=\"moonshotai / kimi-k2-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Kimi-K2-Instruct Description Kimi K2 Instruct is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"moonshotai / kimi-k2-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Kimi-K2-Instruct Description Kimi K2 Instruct is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=moonshotai%20%2F%20kimi-k2-instruct&amp;projectTitle=NIM&amp;description=Kimi-K2-Instruct%20Description%20Kimi%20K2%20Instruct%20is%20a%20state-of-the-art%20mixture-of-experts%20(MoE)%20language%20model%20with%2032%20billion%20activated%20parameters%20and%201%20trillion%20total%20parameters.%20Trained%20with%20the%20Muon%20optimizer%2C%20Kimi%20K2%20achieves%20exceptional%20performance%20across%20frontier%20knowledge%2C%20reasoning%2C%20and%20coding...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=moonshotai%20%2F%20kimi-k2-instruct&amp;projectTitle=NIM&amp;description=Kimi-K2-Instruct%20Description%20Kimi%20K2%20Instruct%20is%20a%20state-of-the-art%20mixture-of-experts%20(MoE)%20language%20model%20with%2032%20billion%20activated%20parameters%20and%201%20trillion%20total%20parameters.%20Trained%20with%20the%20Muon%20optimizer%2C%20Kimi%20K2%20achieves%20exceptional%20performance%20across%20frontier%20knowledge%2C%20reasoning%2C%20and%20coding...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k2-instruct\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1777921742491\"></script><link data-chunk=\"Footer\" rel",
    "source": "https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k2-instruct"
  },
  "moonshotai/kimi-k2-instruct-0905": {
    "fetched_at": 1777970145.0627797,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.709.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"/y8/vbhUwS1h3PR9h/13Tg==:ACyTJ4AzTT51A0eit30Crs1xLtL271ZTOugirI41bf+jERrhiZeflwHhYF6uE/cT2XUoXKf10PFQ6R5qpLEq5Otjc4nrvXLLgMVOg76iUwFJbt4IlY+Sq+BFxHfJDO/puU02BeV/WndCKmBTrvtxyqgaEzAFmqIm+1vKprmTfMoEz4GFVTxevPscZx5cKkLm\"><meta name=\"readme-version\" content=\"1.0\"><title>moonshotai / kimi-k2-instruct-0905</title><meta name=\"description\" content=\"Kimi-K2-Instruct-0905 Description Kimi-K2-Instruct-0905 is the latest, most capable version of Kimi K2, a state-of-the-art Mixture-of-Experts (MoE) language model with 1 trillion total parameters and 32 billion active parameters. It delivers enhanced agentic coding intelligence, improved frontend co...\" data-rh=\"true\"><meta property=\"og:title\" content=\"moonshotai / kimi-k2-instruct-0905\" data-rh=\"true\"><meta property=\"og:description\" content=\"Kimi-K2-Instruct-0905 Description Kimi-K2-Instruct-0905 is the latest, most capable version of Kimi K2, a state-of-the-art Mixture-of-Experts (MoE) language model with 1 trillion total parameters and 32 billion active parameters. It delivers enhanced agentic coding intelligence, improved frontend co...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"moonshotai / kimi-k2-instruct-0905\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Kimi-K2-Instruct-0905 Description Kimi-K2-Instruct-0905 is the latest, most capable version of Kimi K2, a state-of-the-art Mixture-of-Experts (MoE) language model with 1 trillion total parameters and 32 billion active parameters. It delivers enhanced agentic coding intelligence, improved frontend co...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=moonshotai%20%2F%20kimi-k2-instruct-0905&amp;projectTitle=NIM&amp;description=Kimi-K2-Instruct-0905%20Description%20Kimi-K2-Instruct-0905%20is%20the%20latest%2C%20most%20capable%20version%20of%20Kimi%20K2%2C%20a%20state-of-the-art%20Mixture-of-Experts%20(MoE)%20language%20model%20with%201%20trillion%20total%20parameters%20and%2032%20billion%20active%20parameters.%20It%20delivers%20enhanced%20agentic%20coding%20intelligence%2C%20improved%20frontend%20co...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=moonshotai%20%2F%20kimi-k2-instruct-0905&amp;projectTitle=NIM&amp;description=Kimi-K2-Instruct-0905%20Description%20Kimi-K2-Instruct-0905%20is%20the%20latest%2C%20most%20capable%20version%20of%20Kimi%20K2%2C%20a%20state-of-the-art%20Mixture-of-Experts%20(MoE)%20language%20model%20with%201%20trillion%20total%20parameters%20and%2032%20billion%20active%20parameters.%20It%20delivers%20enhanced%20agentic%20coding%20intelligence%2C%20improved%20frontend%20co...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k2-instruct-0905\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1777921742491\"></script><li",
    "source": "https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k2-instruct-0905"
  },
  "moonshotai/kimi-k2-thinking": {
    "fetched_at": 1777970145.787989,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.709.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"SXasF2hI9PiPnc8YT3WytQ==:VkEMoZ53XcPB/HDz77EP1NFKNda0qOmOtO1ybIWXV1aSNcMBNITie+ZXdvJiyzpF8IVE0zciPYLnWl83bFIwCo07fVr/5lJWZLkFrF1scxJhOTLt1FjVB7Ic46rJRdY0ZHNOe6mQj9p3qISrTYZpV/uyyq/dmp6CbNcCIWXbPVkwFhM/olfJ+T/Gfj09Hs08\"><meta name=\"readme-version\" content=\"1.0\"><title>moonshotai / kimi-k2-thinking</title><meta name=\"description\" content=\"Kimi-K2-Thinking Description Kimi K2 Thinking is the most capable open-source thinking model. Starting with Kimi K2 Thinking, we built it as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and othe...\" data-rh=\"true\"><meta property=\"og:title\" content=\"moonshotai / kimi-k2-thinking\" data-rh=\"true\"><meta property=\"og:description\" content=\"Kimi-K2-Thinking Description Kimi K2 Thinking is the most capable open-source thinking model. Starting with Kimi K2 Thinking, we built it as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and othe...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"moonshotai / kimi-k2-thinking\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Kimi-K2-Thinking Description Kimi K2 Thinking is the most capable open-source thinking model. Starting with Kimi K2 Thinking, we built it as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and othe...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=moonshotai%20%2F%20kimi-k2-thinking&amp;projectTitle=NIM&amp;description=Kimi-K2-Thinking%20Description%20Kimi%20K2%20Thinking%20is%20the%20most%20capable%20open-source%20thinking%20model.%20Starting%20with%20Kimi%20K2%20Thinking%2C%20we%20built%20it%20as%20a%20thinking%20agent%20that%20reasons%20step-by-step%20while%20dynamically%20invoking%20tools.%20It%20sets%20a%20new%20state-of-the-art%20on%20Humanity's%20Last%20Exam%20(HLE)%2C%20BrowseComp%2C%20and%20othe...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=moonshotai%20%2F%20kimi-k2-thinking&amp;projectTitle=NIM&amp;description=Kimi-K2-Thinking%20Description%20Kimi%20K2%20Thinking%20is%20the%20most%20capable%20open-source%20thinking%20model.%20Starting%20with%20Kimi%20K2%20Thinking%2C%20we%20built%20it%20as%20a%20thinking%20agent%20that%20reasons%20step-by-step%20while%20dynamically%20invoking%20tools.%20It%20sets%20a%20new%20state-of-the-art%20on%20Humanity's%20Last%20Exam%20(HLE)%2C%20BrowseComp%2C%20and%20othe...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k2-thinking\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1777921742491\"></script><link",
    "source": "https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k2-thinking"
  },
  "nvidia/embed-qa-4": {
    "fetched_at": 1779873820.345869,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"b1L67MTpsCC4GGMCkho3Ng==:TlIwuaOQ30vMd/pJ9Xh5DJzSvBOxeKTwxSs1bPcJP8WnVSsa3H3nlV4UtG05rH8SDr1Y2k8rwQqKkb5EFTu+ntzXuB7Ox1FtGl0r/qd5xlh/cboCd1dnKBttLrCQKlRhZtImWlr8eoSeKtvmnJj4SJ9qBYF2b/KWfWg3EaeyBeHnB9iTtZQrCPPldX9dJ39Q\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / embed-qa-4</title><meta name=\"description\" content=\"Model Overview Description The NVIDIA Retrieval QA Embedding Model is an embedding model optimized for text question-answering retrieval. An embedding model is a crucial component of a text retrieval system, as it transforms textual information into dense vector representations. They are typically t...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / embed-qa-4\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description The NVIDIA Retrieval QA Embedding Model is an embedding model optimized for text question-answering retrieval. An embedding model is a crucial component of a text retrieval system, as it transforms textual information into dense vector representations. They are typically t...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / embed-qa-4\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description The NVIDIA Retrieval QA Embedding Model is an embedding model optimized for text question-answering retrieval. An embedding model is a crucial component of a text retrieval system, as it transforms textual information into dense vector representations. They are typically t...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20embed-qa-4&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20The%20NVIDIA%20Retrieval%20QA%20Embedding%20Model%20is%20an%20embedding%20model%20optimized%20for%20text%20question-answering%20retrieval.%20An%20embedding%20model%20is%20a%20crucial%20component%20of%20a%20text%20retrieval%20system%2C%20as%20it%20transforms%20textual%20information%20into%20dense%20vector%20representations.%20They%20are%20typically%20t...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20embed-qa-4&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20The%20NVIDIA%20Retrieval%20QA%20Embedding%20Model%20is%20an%20embedding%20model%20optimized%20for%20text%20question-answering%20retrieval.%20An%20embedding%20model%20is%20a%20crucial%20component%20of%20a%20text%20retrieval%20system%2C%20as%20it%20transforms%20textual%20information%20into%20dense%20vector%20representations.%20They%20are%20typically%20t...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-embed-qa-4\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"https://cdn.readme.i",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-embed-qa-4"
  },
  "nvidia/gliner-pii": {
    "fetched_at": 1779873820.5701256,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"N8xX93wiNNFBzYtaLJAR1Q==:YEmskpNs3o6bgf0aiVjec800qFwb6BaXgUB+DpjavjAjN5nRdFcfiy7VCrqMkhCBNxF4bD43rCosYm2zAwLRfbt3ROZ3VAiBzD60d/pjwgqHnXS+iJtOpgE+xHMCrpG1+Do1rfkrGsp/rVuwaG/TX8dEP7PimKYv9f6dhZ4EU3glxIGOAJWZogXH0iMvAd7o\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / gliner-pii</title><meta name=\"description\" content=\"Model Overview GLiNER PII is a successor to the Gretel GLiNER PII/PHI models. Built on the GLiNER bi-large base, it detects and classifies a broad range of Personally Identifiable Information (PII) and Protected Health Information (PHI) in structured and unstructured text. It is non-generative and p...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / gliner-pii\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview GLiNER PII is a successor to the Gretel GLiNER PII/PHI models. Built on the GLiNER bi-large base, it detects and classifies a broad range of Personally Identifiable Information (PII) and Protected Health Information (PHI) in structured and unstructured text. It is non-generative and p...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / gliner-pii\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview GLiNER PII is a successor to the Gretel GLiNER PII/PHI models. Built on the GLiNER bi-large base, it detects and classifies a broad range of Personally Identifiable Information (PII) and Protected Health Information (PHI) in structured and unstructured text. It is non-generative and p...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20gliner-pii&amp;projectTitle=NIM&amp;description=Model%20Overview%20GLiNER%20PII%20is%20a%20successor%20to%20the%20Gretel%20GLiNER%20PII%2FPHI%20models.%20Built%20on%20the%20GLiNER%20bi-large%20base%2C%20it%20detects%20and%20classifies%20a%20broad%20range%20of%20Personally%20Identifiable%20Information%20(PII)%20and%20Protected%20Health%20Information%20(PHI)%20in%20structured%20and%20unstructured%20text.%20It%20is%20non-generative%20and%20p...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20gliner-pii&amp;projectTitle=NIM&amp;description=Model%20Overview%20GLiNER%20PII%20is%20a%20successor%20to%20the%20Gretel%20GLiNER%20PII%2FPHI%20models.%20Built%20on%20the%20GLiNER%20bi-large%20base%2C%20it%20detects%20and%20classifies%20a%20broad%20range%20of%20Personally%20Identifiable%20Information%20(PII)%20and%20Protected%20Health%20Information%20(PHI)%20in%20structured%20and%20unstructured%20text.%20It%20is%20non-generative%20and%20p...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-gliner-pii\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"http",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-gliner-pii"
  },
  "nvidia/ising-calibration-1-35b-a3b": {
    "fetched_at": 1779873821.1704605,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"581DiXtN/OSxsIoX+f+CXg==:yVj5wioZeH+1KJEoJaxeKnnPacyj2Jwkq1MDQXFI2bsbLzgQ9Ny88F3+kS3wxAUtU3wRZlxN9EzkMTf2uopI8qGElcgt2FcETrW2exJ2K8qqLZIAzr2pdYMWfPVzqY0o6Dn2hrPCwkpZRD5+j1zwERmcbnckjhl/vGOEqXs57AZTj6Xa2cHj69ob5Di/PSuv\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / ising-calibration-1-35b-a3b</title><meta name=\"description\" content=\"Model Overview Description: Ising-Calibration-1-35B-A3B analyzes quantum computing calibration experiment plots and generates structured technical text across six analysis question categories. Ising-Calibration-1-35B-A3B was developed by NVIDIA as a quantum calibration vision-language model built on...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / ising-calibration-1-35b-a3b\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description: Ising-Calibration-1-35B-A3B analyzes quantum computing calibration experiment plots and generates structured technical text across six analysis question categories. Ising-Calibration-1-35B-A3B was developed by NVIDIA as a quantum calibration vision-language model built on...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / ising-calibration-1-35b-a3b\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description: Ising-Calibration-1-35B-A3B analyzes quantum computing calibration experiment plots and generates structured technical text across six analysis question categories. Ising-Calibration-1-35B-A3B was developed by NVIDIA as a quantum calibration vision-language model built on...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20ising-calibration-1-35b-a3b&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20Ising-Calibration-1-35B-A3B%20analyzes%20quantum%20computing%20calibration%20experiment%20plots%20and%20generates%20structured%20technical%20text%20across%20six%20analysis%20question%20categories.%20Ising-Calibration-1-35B-A3B%20was%20developed%20by%20NVIDIA%20as%20a%20quantum%20calibration%20vision-language%20model%20built%20on...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20ising-calibration-1-35b-a3b&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20Ising-Calibration-1-35B-A3B%20analyzes%20quantum%20computing%20calibration%20experiment%20plots%20and%20generates%20structured%20technical%20text%20across%20six%20analysis%20question%20categories.%20Ising-Calibration-1-35B-A3B%20was%20developed%20by%20NVIDIA%20as%20a%20quantum%20calibration%20vision-language%20model%20built%20on...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-ising-calibration-1-35b-a3b\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chun",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-ising-calibration-1-35b-a3b"
  },
  "nvidia/llama-nemotron-embed-1b-v2": {
    "fetched_at": 1779873822.4111176,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"wI1+306iSIGUdkYKoJttdQ==:obnhHmQZRymL+3cimqOe9OfnRBiGLK/G9oapynl42NzOjV1NHiXsa4DKOOYPWj6SMaekTjqSoRhhChZQnAIkgRjUuFKLi0Gzgs8hGnhuRJAIQ7f226OhN4ptXx9zEDQ6b0nZL37SOK94XrrVPWiFT6E49aAqi8ejG69TO/l+FyAGCId4XOv4Ew+eijxriTCZ\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / llama-nemotron-embed-1b-v2</title><meta name=\"description\" content=\"Model Overview Description: llama-nemotron-embed-1b-v2 is optimized for multilingual and cross-lingual text question-answering retrieval with support for long documents (up to 8192 tokens) and dynamic embedding size (Matryoshka embeddings) . The model was evaluated across 26 languages: English, Arab...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / llama-nemotron-embed-1b-v2\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description: llama-nemotron-embed-1b-v2 is optimized for multilingual and cross-lingual text question-answering retrieval with support for long documents (up to 8192 tokens) and dynamic embedding size (Matryoshka embeddings) . The model was evaluated across 26 languages: English, Arab...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / llama-nemotron-embed-1b-v2\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description: llama-nemotron-embed-1b-v2 is optimized for multilingual and cross-lingual text question-answering retrieval with support for long documents (up to 8192 tokens) and dynamic embedding size (Matryoshka embeddings) . The model was evaluated across 26 languages: English, Arab...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20llama-nemotron-embed-1b-v2&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20llama-nemotron-embed-1b-v2%20is%20optimized%20for%20multilingual%20and%20cross-lingual%20text%20question-answering%20retrieval%20with%20support%20for%20long%20documents%20(up%20to%208192%20tokens)%20and%20dynamic%20embedding%20size%20(Matryoshka%20embeddings)%20.%20The%20model%20was%20evaluated%20across%2026%20languages%3A%20English%2C%20Arab...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20llama-nemotron-embed-1b-v2&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20llama-nemotron-embed-1b-v2%20is%20optimized%20for%20multilingual%20and%20cross-lingual%20text%20question-answering%20retrieval%20with%20support%20for%20long%20documents%20(up%20to%208192%20tokens)%20and%20dynamic%20embedding%20size%20(Matryoshka%20embeddings)%20.%20The%20model%20was%20evaluated%20across%2026%20languages%3A%20English%2C%20Arab...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-llama-nemotron-embed-1b-v2\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-llama-nemotron-embed-1b-v2"
  },
  "nvidia/llama-nemotron-embed-vl-1b-v2": {
    "fetched_at": 1779873822.487575,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"NAz7ZGs4IqSu3g9X+8Fy7Q==:qlp7k7fnoRt/ld+h8f8FPS7c4lQDNs2pjWx3qJzaGgxSdd1XqCB6eb87FvAteL2HAoAVi5D5+daIyab/IlLa15kR29TOOUzOVQR5UquaQaWMZewfnwrjnJfCug7+9UESVx9l07PRtMtO5KL8Er6b5HemJ+i/nFAA3u6yVlJPTGbJ73fL20aiZm1Smv01ss49\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / llama-nemotron-embed-vl-1b-v2</title><meta name=\"description\" content=\"Llama-Nemotron-Embed-VL-1B-v2 Description The Llama-Nemotron-Embed-VL-1B-v2 model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text combined. Documents can be retrieved given a user query in text form. The model su...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / llama-nemotron-embed-vl-1b-v2\" data-rh=\"true\"><meta property=\"og:description\" content=\"Llama-Nemotron-Embed-VL-1B-v2 Description The Llama-Nemotron-Embed-VL-1B-v2 model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text combined. Documents can be retrieved given a user query in text form. The model su...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / llama-nemotron-embed-vl-1b-v2\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Llama-Nemotron-Embed-VL-1B-v2 Description The Llama-Nemotron-Embed-VL-1B-v2 model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text combined. Documents can be retrieved given a user query in text form. The model su...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20llama-nemotron-embed-vl-1b-v2&amp;projectTitle=NIM&amp;description=Llama-Nemotron-Embed-VL-1B-v2%20Description%20The%20Llama-Nemotron-Embed-VL-1B-v2%20model%20is%20optimized%20for%20multimodal%20question-answering%20retrieval.%20The%20model%20can%20embed%20'documents'%20in%20the%20form%20of%20image%2C%20text%2C%20or%20image%20and%20text%20combined.%20Documents%20can%20be%20retrieved%20given%20a%20user%20query%20in%20text%20form.%20The%20model%20su...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20llama-nemotron-embed-vl-1b-v2&amp;projectTitle=NIM&amp;description=Llama-Nemotron-Embed-VL-1B-v2%20Description%20The%20Llama-Nemotron-Embed-VL-1B-v2%20model%20is%20optimized%20for%20multimodal%20question-answering%20retrieval.%20The%20model%20can%20embed%20'documents'%20in%20the%20form%20of%20image%2C%20text%2C%20or%20image%20and%20text%20combined.%20Documents%20can%20be%20retrieved%20given%20a%20user%20query%20in%20text%20form.%20The%20model%20su...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-llama-nemotron-embed-vl-1b-v2\"><script src=\"https://cdn.readme.io/public/js/cash-do",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-llama-nemotron-embed-vl-1b-v2"
  },
  "nvidia/nemoretriever-parse": {
    "fetched_at": 1779873823.2991405,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"K59TaAcag8HqRN1WJb+M0A==:BjulwbWOT8aggOn/0Yl5qhJzxjy/skaxHJAU8ok9FZO7y+own09qevHN9sG9dzB9bp74gwC6v5oF/ZEB0htIrUJUcpSe3nS1g47ElqnBGwy8vS2tVGvEofBFgXxYS3NmXc3ZfoAPrypGWTs1bM83hbl9ltSMK15Rhbeo96BawUCPn8WQ8WD3XvnGE6voYxFF\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nemoretriever-parse</title><meta name=\"description\" content=\"nemoretriever-parse Overview Description: nemoretriever-parse is a general purpose text-extraction model, specifically designed to handle documents. Given an image, nemoretriever-parse is able to extract formatted-text, with bounding-boxes and the corresponding semantic class. This has downstream be...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nemoretriever-parse\" data-rh=\"true\"><meta property=\"og:description\" content=\"nemoretriever-parse Overview Description: nemoretriever-parse is a general purpose text-extraction model, specifically designed to handle documents. Given an image, nemoretriever-parse is able to extract formatted-text, with bounding-boxes and the corresponding semantic class. This has downstream be...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nemoretriever-parse\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"nemoretriever-parse Overview Description: nemoretriever-parse is a general purpose text-extraction model, specifically designed to handle documents. Given an image, nemoretriever-parse is able to extract formatted-text, with bounding-boxes and the corresponding semantic class. This has downstream be...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemoretriever-parse&amp;projectTitle=NIM&amp;description=nemoretriever-parse%20Overview%20Description%3A%20nemoretriever-parse%20is%20a%20general%20purpose%20text-extraction%20model%2C%20specifically%20designed%20to%20handle%20documents.%20Given%20an%20image%2C%20nemoretriever-parse%20is%20able%20to%20extract%20formatted-text%2C%20with%20bounding-boxes%20and%20the%20corresponding%20semantic%20class.%20This%20has%20downstream%20be...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemoretriever-parse&amp;projectTitle=NIM&amp;description=nemoretriever-parse%20Overview%20Description%3A%20nemoretriever-parse%20is%20a%20general%20purpose%20text-extraction%20model%2C%20specifically%20designed%20to%20handle%20documents.%20Given%20an%20image%2C%20nemoretriever-parse%20is%20able%20to%20extract%20formatted-text%2C%20with%20bounding-boxes%20and%20the%20corresponding%20semantic%20class.%20This%20has%20downstream%20be...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nemoretriever-parse\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nemoretriever-parse"
  },
  "nvidia/nemotron-3-content-safety": {
    "fetched_at": 1779873823.9589322,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"/s9cjC8+aIfpRqIiyCxb0g==:jmDzwNet8inZZLSNcPPmLDPZK8Zm77bOxbAb9x5e4G0seCNmVjkyfOgIFpKqj1FiVBH5Vl0wRBriAA+6WFQEjf3Bmxgd9D/xD3VVMEX3cs1hfSptRPCVMf0SD7LRZFORRCNKI+R3lrr8xTfx2ja2K8BeqPh27oOOUXbQPgKz2EjVDkyypJypS5PD9y41axlH\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nemotron-3-content-safety</title><meta name=\"description\" content=\"Nemotron 3 Content Safety Model Model Overview The Nemotron 3 Content Safety model is a small language model (SLM) that uses Google's Gemma-3-4B-it as the base and is fine-tuned by NVIDIA on multimodal and multilingual content-safety related datasets. It can act as a content-safety moderator for bot...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nemotron-3-content-safety\" data-rh=\"true\"><meta property=\"og:description\" content=\"Nemotron 3 Content Safety Model Model Overview The Nemotron 3 Content Safety model is a small language model (SLM) that uses Google's Gemma-3-4B-it as the base and is fine-tuned by NVIDIA on multimodal and multilingual content-safety related datasets. It can act as a content-safety moderator for bot...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nemotron-3-content-safety\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Nemotron 3 Content Safety Model Model Overview The Nemotron 3 Content Safety model is a small language model (SLM) that uses Google's Gemma-3-4B-it as the base and is fine-tuned by NVIDIA on multimodal and multilingual content-safety related datasets. It can act as a content-safety moderator for bot...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-3-content-safety&amp;projectTitle=NIM&amp;description=Nemotron%203%20Content%20Safety%20Model%20Model%20Overview%20The%20Nemotron%203%20Content%20Safety%20model%20is%20a%20small%20language%20model%20(SLM)%20that%20uses%20Google's%20Gemma-3-4B-it%20as%20the%20base%20and%20is%20fine-tuned%20by%20NVIDIA%20on%20multimodal%20and%20multilingual%20content-safety%20related%20datasets.%20It%20can%20act%20as%20a%20content-safety%20moderator%20for%20bot...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-3-content-safety&amp;projectTitle=NIM&amp;description=Nemotron%203%20Content%20Safety%20Model%20Model%20Overview%20The%20Nemotron%203%20Content%20Safety%20model%20is%20a%20small%20language%20model%20(SLM)%20that%20uses%20Google's%20Gemma-3-4B-it%20as%20the%20base%20and%20is%20fine-tuned%20by%20NVIDIA%20on%20multimodal%20and%20multilingual%20content-safety%20related%20datasets.%20It%20can%20act%20as%20a%20content-safety%20moderator%20for%20bot...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3-content-safety\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3-content-safety"
  },
  "nvidia/nemotron-3-nano-30b-a3b": {
    "fetched_at": 1779873823.0524826,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"Aa7iDycAj7UmbJ+9caHcTA==:72tUvVoHRH4jafXMoC2oEQ5gXny/UUQlHwZwnuiC6SYjHJSRBosHzh7j420t9+HOnJXFFN2rNroWy3Qs9LaurVchKwM0x2YRm3oxjIpDyAF9Ch5j+GrhYmunW0pbAX3ysj9EAmIk7tSbJAwq5BtPOL7RhjIs8xSRu0hSZl8HgVDbefa2+VqpTJCgeozn+fWc\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nemotron-3-nano-30b-a3b</title><meta name=\"description\" content=\"Model Overview Model Developer: NVIDIA Corporation Model Dates: September 2025 - December 2025 Data Freshness: The post-training data has a cutoff date of November 28, 2025. The pre-training data has a cutoff date of June 25, 2025. Description Nemotron-3-Nano-30B-A3B is a large language model (LLM) ...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nemotron-3-nano-30b-a3b\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Model Developer: NVIDIA Corporation Model Dates: September 2025 - December 2025 Data Freshness: The post-training data has a cutoff date of November 28, 2025. The pre-training data has a cutoff date of June 25, 2025. Description Nemotron-3-Nano-30B-A3B is a large language model (LLM) ...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nemotron-3-nano-30b-a3b\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Model Developer: NVIDIA Corporation Model Dates: September 2025 - December 2025 Data Freshness: The post-training data has a cutoff date of November 28, 2025. The pre-training data has a cutoff date of June 25, 2025. Description Nemotron-3-Nano-30B-A3B is a large language model (LLM) ...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-3-nano-30b-a3b&amp;projectTitle=NIM&amp;description=Model%20Overview%20Model%20Developer%3A%20NVIDIA%20Corporation%20Model%20Dates%3A%20September%202025%20-%20December%202025%20Data%20Freshness%3A%20The%20post-training%20data%20has%20a%20cutoff%20date%20of%20November%2028%2C%202025.%20The%20pre-training%20data%20has%20a%20cutoff%20date%20of%20June%2025%2C%202025.%20Description%20Nemotron-3-Nano-30B-A3B%20is%20a%20large%20language%20model%20(LLM)%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-3-nano-30b-a3b&amp;projectTitle=NIM&amp;description=Model%20Overview%20Model%20Developer%3A%20NVIDIA%20Corporation%20Model%20Dates%3A%20September%202025%20-%20December%202025%20Data%20Freshness%3A%20The%20post-training%20data%20has%20a%20cutoff%20date%20of%20November%2028%2C%202025.%20The%20pre-training%20data%20has%20a%20cutoff%20date%20of%20June%2025%2C%202025.%20Description%20Nemotron-3-Nano-30B-A3B%20is%20a%20large%20language%20model%20(LLM)%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3-nano-30b-a3b\"><script src=\"https://cdn.readme.io/public/js/cash-dom.mi",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3-nano-30b-a3b"
  },
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
    "fetched_at": 1779873823.1647513,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"vJ6hKyp8ifs1hS4qFWobyg==:+Ee/to95w4B5uug2BBXJxFJaeCB6H8glV3VlRuma45Hh1CIex5/BuFtIrO4VhdqyXNlu1n8GJ12N3ssClnm1nygvvwO1LlbdGd3/oLQWc0KHfZr2PNDCVh+nsWdF2LLPDqdi1ANlAxtAFfkr4/SNwPQm0EaPcrmeyZqmmHAHvhABYWKTUDfBNwktOoRKBlrG\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nemotron-3-nano-omni-30b-a3b-reasoning</title><meta name=\"description\" content=\"Model Overview Description: NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&amp;amp;A, summarization, transcription, and document intelligence workflows. It extends the Nemotron Nano family with integ...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nemotron-3-nano-omni-30b-a3b-reasoning\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description: NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&amp;amp;A, summarization, transcription, and document intelligence workflows. It extends the Nemotron Nano family with integ...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nemotron-3-nano-omni-30b-a3b-reasoning\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description: NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&amp;amp;A, summarization, transcription, and document intelligence workflows. It extends the Nemotron Nano family with integ...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-3-nano-omni-30b-a3b-reasoning&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20NVIDIA%20Nemotron%203%20Nano%20Omni%20is%20a%20multimodal%20large%20language%20model%20that%20unifies%20video%2C%20audio%2C%20image%2C%20and%20text%20understanding%20to%20support%20enterprise-grade%20Q%26amp%3BA%2C%20summarization%2C%20transcription%2C%20and%20document%20intelligence%20workflows.%20It%20extends%20the%20Nemotron%20Nano%20family%20with%20integ...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-3-nano-omni-30b-a3b-reasoning&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20NVIDIA%20Nemotron%203%20Nano%20Omni%20is%20a%20multimodal%20large%20language%20model%20that%20unifies%20video%2C%20audio%2C%20image%2C%20and%20text%20understanding%20to%20support%20enterprise-grade%20Q%26amp%3BA%2C%20summarization%2C%20transcription%2C%20and%20document%20intelligence%20workflows.%20It%20extends%20the%20Nemotron%20Nano%20family%20with%20integ...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-ne",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning"
  },
  "nvidia/nemotron-3-super-120b-a12b": {
    "fetched_at": 1779873823.2721245,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"+ezN/JjOKVlz4gihqRebhA==:PmpHSUtXj9NC1HIZwS3O9O6SgWQ5zvlAWz05nGcHODtjnspU4Y7wvFXBGzct5CJNe0r5r72uKztt9I/Hmpe/f8k/v2j4gTn1e0MuwWVScNRVbafrdTBZn03ysyn9q6p7K/1dyFUw67aEs4s7jErLPz8u9EjCJKdzLfyvy7Be67g4nD0xFJgxuasoBmI22GhT\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nemotron-3-super-120b-a12b</title><meta name=\"description\" content=\"NVIDIA-Nemotron-3-Super-120B-A12B Model Summary Total Parameters 120B (12B active) Architecture LatentMoE - Mamba-2 + MoE + Attention hybrid with Multi-Token Prediction (MTP) Context Length Up to 1M tokens Minimum GPU Requirement 8\u00d7 H100-80GB Supported Languages English, French, German, Italian, Jap...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nemotron-3-super-120b-a12b\" data-rh=\"true\"><meta property=\"og:description\" content=\"NVIDIA-Nemotron-3-Super-120B-A12B Model Summary Total Parameters 120B (12B active) Architecture LatentMoE - Mamba-2 + MoE + Attention hybrid with Multi-Token Prediction (MTP) Context Length Up to 1M tokens Minimum GPU Requirement 8\u00d7 H100-80GB Supported Languages English, French, German, Italian, Jap...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nemotron-3-super-120b-a12b\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"NVIDIA-Nemotron-3-Super-120B-A12B Model Summary Total Parameters 120B (12B active) Architecture LatentMoE - Mamba-2 + MoE + Attention hybrid with Multi-Token Prediction (MTP) Context Length Up to 1M tokens Minimum GPU Requirement 8\u00d7 H100-80GB Supported Languages English, French, German, Italian, Jap...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-3-super-120b-a12b&amp;projectTitle=NIM&amp;description=NVIDIA-Nemotron-3-Super-120B-A12B%20Model%20Summary%20Total%20Parameters%20120B%20(12B%20active)%20Architecture%20LatentMoE%20-%20Mamba-2%20%2B%20MoE%20%2B%20Attention%20hybrid%20with%20Multi-Token%20Prediction%20(MTP)%20Context%20Length%20Up%20to%201M%20tokens%20Minimum%20GPU%20Requirement%208%C3%97%20H100-80GB%20Supported%20Languages%20English%2C%20French%2C%20German%2C%20Italian%2C%20Jap...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-3-super-120b-a12b&amp;projectTitle=NIM&amp;description=NVIDIA-Nemotron-3-Super-120B-A12B%20Model%20Summary%20Total%20Parameters%20120B%20(12B%20active)%20Architecture%20LatentMoE%20-%20Mamba-2%20%2B%20MoE%20%2B%20Attention%20hybrid%20with%20Multi-Token%20Prediction%20(MTP)%20Context%20Length%20Up%20to%201M%20tokens%20Minimum%20GPU%20Requirement%208%C3%97%20H100-80GB%20Supported%20Languages%20English%2C%20French%2C%20German%2C%20Italian%2C%20Jap...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3-super-120b-a12b\"><script src=\"https://cdn.readme.io/public/js/cash-do",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3-super-120b-a12b"
  },
  "nvidia/nemotron-content-safety-reasoning-4b": {
    "fetched_at": 1779873824.1780498,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"3OoIx2R8A46IaL7d0mVg8w==:cPo7G7+zD7EFX7f7ueCODye9VH9o/VY8pmlLKk6eMf378qupl0/Q/gyYfowParfoVzbVWxWdT2G5SntL7gVAIEToMn1RfH6FdWVcC2xShj5usm2WB3Lzagxwt/4wW0J/2NlRtqRgH+6y1XDCE+0ho85rIsSY6Qn2jUGvey950GJ+aJKv7d45GUW0z7khQj50\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nemotron-content-safety-reasoning-4b</title><meta name=\"description\" content=\"NVIDIA-Nemotron-Content-Safety-Reasoning-4B Overview Description Nemotron-Content-Safety-Reasoning-4B is a Large Language Model (LLM) classifier designed to function as a dynamic and adaptable guardrail for content safety and dialogue moderation (topic-following). Its primary advantage is the abilit...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nemotron-content-safety-reasoning-4b\" data-rh=\"true\"><meta property=\"og:description\" content=\"NVIDIA-Nemotron-Content-Safety-Reasoning-4B Overview Description Nemotron-Content-Safety-Reasoning-4B is a Large Language Model (LLM) classifier designed to function as a dynamic and adaptable guardrail for content safety and dialogue moderation (topic-following). Its primary advantage is the abilit...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nemotron-content-safety-reasoning-4b\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"NVIDIA-Nemotron-Content-Safety-Reasoning-4B Overview Description Nemotron-Content-Safety-Reasoning-4B is a Large Language Model (LLM) classifier designed to function as a dynamic and adaptable guardrail for content safety and dialogue moderation (topic-following). Its primary advantage is the abilit...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-content-safety-reasoning-4b&amp;projectTitle=NIM&amp;description=NVIDIA-Nemotron-Content-Safety-Reasoning-4B%20Overview%20Description%20Nemotron-Content-Safety-Reasoning-4B%20is%20a%20Large%20Language%20Model%20(LLM)%20classifier%20designed%20to%20function%20as%20a%20dynamic%20and%20adaptable%20guardrail%20for%20content%20safety%20and%20dialogue%20moderation%20(topic-following).%20Its%20primary%20advantage%20is%20the%20abilit...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-content-safety-reasoning-4b&amp;projectTitle=NIM&amp;description=NVIDIA-Nemotron-Content-Safety-Reasoning-4B%20Overview%20Description%20Nemotron-Content-Safety-Reasoning-4B%20is%20a%20Large%20Language%20Model%20(LLM)%20classifier%20designed%20to%20function%20as%20a%20dynamic%20and%20adaptable%20guardrail%20for%20content%20safety%20and%20dialogue%20moderation%20(topic-following).%20Its%20primary%20advantage%20is%20the%20abilit...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-content-safety-reasoning-4b\"><script src=\"https://cdn.readme.io/public/js/cash-",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-content-safety-reasoning-4b"
  },
  "nvidia/nemotron-mini-4b-instruct": {
    "fetched_at": 1779873824.6352162,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"bqf0MwgNjDSYCVmqYn+z9A==:ESURUOvJJ1/h0Rbs6ISMm3iRKI0TSOtPmfefjXPYYzLXIhaf3FWBsjsvueakYouxJPyl0BrNBqZjP1WNDTarYW6GlFOWC2t6SiHrZdy27sEvGAfoToL5j4xHW/2x/FZIVslHXLKUd7Lu4Rl1NA+I/Cc3lnFBJ/aLwplcrhlwUG5/MiRJWKFSFaadqk/9Auso\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nemotron-mini-4b-instruct</title><meta name=\"description\" content=\"Model Overview Description: Nemotron-Mini-4B Instruct is a model for generating responses for roleplaying, retrieval augmented generation, and function calling. It is a small language model (SLM) optimized through distillation, pruning and quantization for speed and on-device deployment. VRAM usage ...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nemotron-mini-4b-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description: Nemotron-Mini-4B Instruct is a model for generating responses for roleplaying, retrieval augmented generation, and function calling. It is a small language model (SLM) optimized through distillation, pruning and quantization for speed and on-device deployment. VRAM usage ...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nemotron-mini-4b-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description: Nemotron-Mini-4B Instruct is a model for generating responses for roleplaying, retrieval augmented generation, and function calling. It is a small language model (SLM) optimized through distillation, pruning and quantization for speed and on-device deployment. VRAM usage ...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-mini-4b-instruct&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20Nemotron-Mini-4B%20Instruct%20is%20a%20model%20for%20generating%20responses%20for%20roleplaying%2C%20retrieval%20augmented%20generation%2C%20and%20function%20calling.%20It%20is%20a%20small%20language%20model%20(SLM)%20optimized%20through%20distillation%2C%20pruning%20and%20quantization%20for%20speed%20and%20on-device%20deployment.%20VRAM%20usage%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-mini-4b-instruct&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20Nemotron-Mini-4B%20Instruct%20is%20a%20model%20for%20generating%20responses%20for%20roleplaying%2C%20retrieval%20augmented%20generation%2C%20and%20function%20calling.%20It%20is%20a%20small%20language%20model%20(SLM)%20optimized%20through%20distillation%2C%20pruning%20and%20quantization%20for%20speed%20and%20on-device%20deployment.%20VRAM%20usage%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-mini-4b-instruct\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?17798319014",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-mini-4b-instruct"
  },
  "nvidia/nemotron-nano-12b-v2-vl": {
    "fetched_at": 1779873824.115083,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"cPLpKzOwhbD7CKwfC3zStg==:yrHXhQ8J3aMKmTQ1Pp7gcryZccdftFx6jD3psJrs1vbgSVOBAI0tfKw2Lyz1+9/Prm2qz/LpOFgEnndLgyJtXmSGYv3DD/PAEzIPaFRiTrAI7weDqmjATId9KNrwQF8bJjn5YIWDWT7Itak24BCQVBzoDdK/heb50y7ZBDMlDtfjcV4+pWU7lkHQLtmkl1H0\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nemotron-nano-12b-v2-vl</title><meta name=\"description\" content=\"Model Overview Description: NVIDIA Nemotron Nano 12B v2 VL model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&amp;amp;A and summarization capabilities. This model is ready for commercial use. License/Terms of Use Governing Terms: The trial serv...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nemotron-nano-12b-v2-vl\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description: NVIDIA Nemotron Nano 12B v2 VL model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&amp;amp;A and summarization capabilities. This model is ready for commercial use. License/Terms of Use Governing Terms: The trial serv...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nemotron-nano-12b-v2-vl\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description: NVIDIA Nemotron Nano 12B v2 VL model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&amp;amp;A and summarization capabilities. This model is ready for commercial use. License/Terms of Use Governing Terms: The trial serv...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-nano-12b-v2-vl&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20NVIDIA%20Nemotron%20Nano%2012B%20v2%20VL%20model%20enables%20multi-image%20reasoning%20and%20video%20understanding%2C%20along%20with%20strong%20document%20intelligence%2C%20visual%20Q%26amp%3BA%20and%20summarization%20capabilities.%20This%20model%20is%20ready%20for%20commercial%20use.%20License%2FTerms%20of%20Use%20Governing%20Terms%3A%20The%20trial%20serv...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-nano-12b-v2-vl&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20NVIDIA%20Nemotron%20Nano%2012B%20v2%20VL%20model%20enables%20multi-image%20reasoning%20and%20video%20understanding%2C%20along%20with%20strong%20document%20intelligence%2C%20visual%20Q%26amp%3BA%20and%20summarization%20capabilities.%20This%20model%20is%20ready%20for%20commercial%20use.%20License%2FTerms%20of%20Use%20Governing%20Terms%3A%20The%20trial%20serv...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-nano-12b-v2-vl\"><script src=\"https://cdn.readme.io/public/js/cash-dom.mi",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-nano-12b-v2-vl"
  },
  "nvidia/nemotron-parse": {
    "fetched_at": 1779873824.343957,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"Mxiiu5vwWSApoVjQ5gdEsQ==:fEb1lzqqzr9HgYbiqz9kUC1JgUS0H/0/cuI0Q3jzQciJvW4t6eSmHmavhrhZglEt8c/7JjJ7n6RAjI6SjrIvgUz3sqDI9tWztsgz4nrERS5c9IeImmMc8m/D0oTH89FBtZJqxQg4SrO8DBghnAw7pj9SW1gJhvVf9DodU1IaJRu1uEIJqE3/BLvqyR18Ya8G\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nemotron-parse</title><meta name=\"description\" content=\"nemotron-parse Overview nemotron-parse is a general purpose text-extraction model, specifically designed to handle documents. Given an image, nemotron-parse is able to extract formatted-text, with bounding-boxes and the corresponding semantic class. This has downstream benefits for several tasks suc...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nemotron-parse\" data-rh=\"true\"><meta property=\"og:description\" content=\"nemotron-parse Overview nemotron-parse is a general purpose text-extraction model, specifically designed to handle documents. Given an image, nemotron-parse is able to extract formatted-text, with bounding-boxes and the corresponding semantic class. This has downstream benefits for several tasks suc...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nemotron-parse\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"nemotron-parse Overview nemotron-parse is a general purpose text-extraction model, specifically designed to handle documents. Given an image, nemotron-parse is able to extract formatted-text, with bounding-boxes and the corresponding semantic class. This has downstream benefits for several tasks suc...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-parse&amp;projectTitle=NIM&amp;description=nemotron-parse%20Overview%20nemotron-parse%20is%20a%20general%20purpose%20text-extraction%20model%2C%20specifically%20designed%20to%20handle%20documents.%20Given%20an%20image%2C%20nemotron-parse%20is%20able%20to%20extract%20formatted-text%2C%20with%20bounding-boxes%20and%20the%20corresponding%20semantic%20class.%20This%20has%20downstream%20benefits%20for%20several%20tasks%20suc...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nemotron-parse&amp;projectTitle=NIM&amp;description=nemotron-parse%20Overview%20nemotron-parse%20is%20a%20general%20purpose%20text-extraction%20model%2C%20specifically%20designed%20to%20handle%20documents.%20Given%20an%20image%2C%20nemotron-parse%20is%20able%20to%20extract%20formatted-text%2C%20with%20bounding-boxes%20and%20the%20corresponding%20semantic%20class.%20This%20has%20downstream%20benefits%20for%20several%20tasks%20suc...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-parse\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"https://",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-parse"
  },
  "nvidia/nv-embed-v1": {
    "fetched_at": 1779873824.7891293,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"AJssff6aRCpePLihsFQRoQ==:wB7CU3Al+q5A+kZB2PGQeLxJ5trY86L0SWS3nul5y9X8IaLYraRKSoNrtSz7ZEnMnv+3SDYXEUiHvtgCkD78V79adkrmjzA5lPNNJWqOYx3MzK4QnEpNHieHdzkA5YFkMvcr3Zaxt0jigWBtPY3kYcGXRCKexJ/+5Olqr9QeU/8X1nlpKL1ZEaCqyfid/VA5\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nv-embed-v1</title><meta name=\"description\" content=\"Model Overview Description The NV-Embed Model is a generalist embedding model that excels across 56 tasks, including retrieval, reranking, classification, clustering, and semantic textual similarity tasks. NV-Embed achieves the highest score of 59.36 on 15 retrieval tasks within this benchmark. NV-E...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nv-embed-v1\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description The NV-Embed Model is a generalist embedding model that excels across 56 tasks, including retrieval, reranking, classification, clustering, and semantic textual similarity tasks. NV-Embed achieves the highest score of 59.36 on 15 retrieval tasks within this benchmark. NV-E...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nv-embed-v1\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description The NV-Embed Model is a generalist embedding model that excels across 56 tasks, including retrieval, reranking, classification, clustering, and semantic textual similarity tasks. NV-Embed achieves the highest score of 59.36 on 15 retrieval tasks within this benchmark. NV-E...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nv-embed-v1&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20The%20NV-Embed%20Model%20is%20a%20generalist%20embedding%20model%20that%20excels%20across%2056%20tasks%2C%20including%20retrieval%2C%20reranking%2C%20classification%2C%20clustering%2C%20and%20semantic%20textual%20similarity%20tasks.%20NV-Embed%20achieves%20the%20highest%20score%20of%2059.36%20on%2015%20retrieval%20tasks%20within%20this%20benchmark.%20NV-E...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nv-embed-v1&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20The%20NV-Embed%20Model%20is%20a%20generalist%20embedding%20model%20that%20excels%20across%2056%20tasks%2C%20including%20retrieval%2C%20reranking%2C%20classification%2C%20clustering%2C%20and%20semantic%20textual%20similarity%20tasks.%20NV-Embed%20achieves%20the%20highest%20score%20of%2059.36%20on%2015%20retrieval%20tasks%20within%20this%20benchmark.%20NV-E...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nv-embed-v1\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"https:",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nv-embed-v1"
  },
  "nvidia/nv-embedcode-7b-v1": {
    "fetched_at": 1779873825.4124851,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"49UaZyeYc+Re82KzsB7HSw==:uVfTg459vp2UG4gP0angeq5Pt/168QB8JBt20aBCPI6UXgXjoojoeouNvD+Q842X+FT3hjQADoaiILJkueiqp6pQaoZZDS2D8pssgQH/H6EESz+j1rCYiZ9MST5kxz+4qOhe0xYN/8YAwoNtJR3WJpPE/bKqn3fJXNliRWaTig05iNp0Qg5TXWsM09nk8O2c\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nv-embedcode-7b-v1</title><meta name=\"description\" content=\"Model Overview Description: The NV-EmbedCode model is a 7B Mistral-based embedding model optimized for code retrieval, supporting text, code, and hybrid queries. Code retrieval is a critical task in many domains including coding assistance, code explanation, summarization, and documentation search. ...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nv-embedcode-7b-v1\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description: The NV-EmbedCode model is a 7B Mistral-based embedding model optimized for code retrieval, supporting text, code, and hybrid queries. Code retrieval is a critical task in many domains including coding assistance, code explanation, summarization, and documentation search. ...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nv-embedcode-7b-v1\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description: The NV-EmbedCode model is a 7B Mistral-based embedding model optimized for code retrieval, supporting text, code, and hybrid queries. Code retrieval is a critical task in many domains including coding assistance, code explanation, summarization, and documentation search. ...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nv-embedcode-7b-v1&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20The%20NV-EmbedCode%20model%20is%20a%207B%20Mistral-based%20embedding%20model%20optimized%20for%20code%20retrieval%2C%20supporting%20text%2C%20code%2C%20and%20hybrid%20queries.%20Code%20retrieval%20is%20a%20critical%20task%20in%20many%20domains%20including%20coding%20assistance%2C%20code%20explanation%2C%20summarization%2C%20and%20documentation%20search.%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nv-embedcode-7b-v1&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%3A%20The%20NV-EmbedCode%20model%20is%20a%207B%20Mistral-based%20embedding%20model%20optimized%20for%20code%20retrieval%2C%20supporting%20text%2C%20code%2C%20and%20hybrid%20queries.%20Code%20retrieval%20is%20a%20critical%20task%20in%20many%20domains%20including%20coding%20assistance%2C%20code%20explanation%2C%20summarization%2C%20and%20documentation%20search.%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nv-embedcode-7b-v1\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-ch",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nv-embedcode-7b-v1"
  },
  "nvidia/nv-embedqa-e5-v5": {
    "fetched_at": 1779873825.4842608,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"/AzC4ZjWHddVvPBPq31uQw==:Epwrfp/HSY6T53lLaxcOAEIBlWdvIMc6n+WiTPBQfaEna+PKVfyl/cfDEcc1qfyDoYZFKYhA19eo354PzL1mLfMpALTWdwYnnYsD/xSz2wYgwk/nzULXjWP6k1JJ/upXL/9ZsTLU/cwa+KJq06RZN3jaMDZ2fWJUR3WrKtEHKopNhmReZ1NNjNqAuRe1mlWq\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nv-embedqa-e5-v5</title><meta name=\"description\" content=\"Model Overview Description The NVIDIA Retrieval QA E5 Embedding Model is an embedding model optimized for text question-answering retrieval. An embedding model is a crucial component of a text retrieval system, as it transforms textual information into dense vector representations. They are typicall...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nv-embedqa-e5-v5\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description The NVIDIA Retrieval QA E5 Embedding Model is an embedding model optimized for text question-answering retrieval. An embedding model is a crucial component of a text retrieval system, as it transforms textual information into dense vector representations. They are typicall...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nv-embedqa-e5-v5\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description The NVIDIA Retrieval QA E5 Embedding Model is an embedding model optimized for text question-answering retrieval. An embedding model is a crucial component of a text retrieval system, as it transforms textual information into dense vector representations. They are typicall...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nv-embedqa-e5-v5&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20The%20NVIDIA%20Retrieval%20QA%20E5%20Embedding%20Model%20is%20an%20embedding%20model%20optimized%20for%20text%20question-answering%20retrieval.%20An%20embedding%20model%20is%20a%20crucial%20component%20of%20a%20text%20retrieval%20system%2C%20as%20it%20transforms%20textual%20information%20into%20dense%20vector%20representations.%20They%20are%20typicall...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nv-embedqa-e5-v5&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20The%20NVIDIA%20Retrieval%20QA%20E5%20Embedding%20Model%20is%20an%20embedding%20model%20optimized%20for%20text%20question-answering%20retrieval.%20An%20embedding%20model%20is%20a%20crucial%20component%20of%20a%20text%20retrieval%20system%2C%20as%20it%20transforms%20textual%20information%20into%20dense%20vector%20representations.%20They%20are%20typicall...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nv-embedqa-e5-v5\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" a",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nv-embedqa-e5-v5"
  },
  "nvidia/nvclip": {
    "fetched_at": 1779873825.0475307,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"r9fyWD7j7Vf0hsFg81sBSw==:ioF/uGafnB4CHXq5uYW8slrg8keEP0O4KEPOSjVgWft+rrZdiN8V2LlXP0dAe1JY3s80zO6FzNisKYt4pgt77D/m0u8+YHwwq2mKLGMRNSTQAE6sT5PpF6FBxx4D/JJzqOlkRb1/NfddlZgV86qv/g19odYuDCTrwx+lhkZ7XIUIJUAkmkLpX4HVxopXKl+K\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nvclip</title><meta name=\"description\" content=\"NV-CLIP (Commercial Foundation Model) Model Overview NV-CLIP is a multimodal embeddings model for image and text. Trained on 700M proprietary images, NV-CLIP is the NVIDIA commercial version of OpenAI\u2019s CLIP (Contrastive Language-Image Pre-Training) model. NV-CLIP can be applied to various areas suc...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nvclip\" data-rh=\"true\"><meta property=\"og:description\" content=\"NV-CLIP (Commercial Foundation Model) Model Overview NV-CLIP is a multimodal embeddings model for image and text. Trained on 700M proprietary images, NV-CLIP is the NVIDIA commercial version of OpenAI\u2019s CLIP (Contrastive Language-Image Pre-Training) model. NV-CLIP can be applied to various areas suc...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nvclip\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"NV-CLIP (Commercial Foundation Model) Model Overview NV-CLIP is a multimodal embeddings model for image and text. Trained on 700M proprietary images, NV-CLIP is the NVIDIA commercial version of OpenAI\u2019s CLIP (Contrastive Language-Image Pre-Training) model. NV-CLIP can be applied to various areas suc...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nvclip&amp;projectTitle=NIM&amp;description=NV-CLIP%20(Commercial%20Foundation%20Model)%20Model%20Overview%20NV-CLIP%20is%20a%20multimodal%20embeddings%20model%20for%20image%20and%20text.%20Trained%20on%20700M%20proprietary%20images%2C%20NV-CLIP%20is%20the%20NVIDIA%20commercial%20version%20of%20OpenAI%E2%80%99s%20CLIP%20(Contrastive%20Language-Image%20Pre-Training)%20model.%20NV-CLIP%20can%20be%20applied%20to%20various%20areas%20suc...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nvclip&amp;projectTitle=NIM&amp;description=NV-CLIP%20(Commercial%20Foundation%20Model)%20Model%20Overview%20NV-CLIP%20is%20a%20multimodal%20embeddings%20model%20for%20image%20and%20text.%20Trained%20on%20700M%20proprietary%20images%2C%20NV-CLIP%20is%20the%20NVIDIA%20commercial%20version%20of%20OpenAI%E2%80%99s%20CLIP%20(Contrastive%20Language-Image%20Pre-Training)%20model.%20NV-CLIP%20can%20be%20applied%20to%20various%20areas%20suc...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nvclip\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"https://cdn.readme.io/public/hub",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nvclip"
  },
  "nvidia/nvidia-nemotron-nano-9b-v2": {
    "fetched_at": 1779873826.233448,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"kM64FL6+Mf5qI2ICt/VIqg==:GP9fUliS94GoWehb/RM9c5TsajBnLydj+lGrGI6bVTyFtQVDvMK5cwrPnZoNkf1j7obt23XuSoihVs7RONMyc9CuzNM0oUOGC0aVDzyW5qOQwlqd46wHlGHcFVLvJwmB7IAAa2TBKkcsCAtFyUfvMBH6OK+HTEaVQFdc+COVb66Q0A2PLRvFbzGKYuyi2Prb\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / nvidia-nemotron-nano-9b-v2</title><meta name=\"description\" content=\"NVIDIA-Nemotron-Nano-9B-v2 Overview NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding w...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / nvidia-nemotron-nano-9b-v2\" data-rh=\"true\"><meta property=\"og:description\" content=\"NVIDIA-Nemotron-Nano-9B-v2 Overview NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding w...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / nvidia-nemotron-nano-9b-v2\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"NVIDIA-Nemotron-Nano-9B-v2 Overview NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding w...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nvidia-nemotron-nano-9b-v2&amp;projectTitle=NIM&amp;description=NVIDIA-Nemotron-Nano-9B-v2%20Overview%20NVIDIA-Nemotron-Nano-9B-v2%20is%20a%20large%20language%20model%20(LLM)%20trained%20from%20scratch%20by%20NVIDIA%2C%20and%20designed%20as%20a%20unified%20model%20for%20both%20reasoning%20and%20non-reasoning%20tasks.%20It%20responds%20to%20user%20queries%20and%20tasks%20by%20first%20generating%20a%20reasoning%20trace%20and%20then%20concluding%20w...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20nvidia-nemotron-nano-9b-v2&amp;projectTitle=NIM&amp;description=NVIDIA-Nemotron-Nano-9B-v2%20Overview%20NVIDIA-Nemotron-Nano-9B-v2%20is%20a%20large%20language%20model%20(LLM)%20trained%20from%20scratch%20by%20NVIDIA%2C%20and%20designed%20as%20a%20unified%20model%20for%20both%20reasoning%20and%20non-reasoning%20tasks.%20It%20responds%20to%20user%20queries%20and%20tasks%20by%20first%20generating%20a%20reasoning%20trace%20and%20then%20concluding%20w...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-nvidia-nemotron-nano-9b-v2\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?17798",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-nvidia-nemotron-nano-9b-v2"
  },
  "nvidia/vila": {
    "fetched_at": 1779531651.0964603,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.745.0\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"nAfwmh4GX1tr4epEvsZWig==:Mm+TdUeshkXQpWow63MZtmUeoI0LNfY5kWC6o3Q5DZn6M1WPCKxAYVBhq2i3eIsRfBfCxYkuEnyO/FQjHDiDYFcG549R7Ixb/UrUG+SJiAQ9iHxnzzffWeEgsvyjLKP/IQP3RQHcJ2vSmq8xpC4H6vRvIm/K1u/P4q8QxjO87kp0/Jb2LMSeeVSOpHF440NE\"><meta name=\"readme-version\" content=\"1.0\"><title>nvidia / vila</title><meta name=\"description\" content=\"Vila Model Card Description NVIDIA Vila is a leading vision language model (VLMs) that enables the ability to query and summarize images and video from the physical or virtual world. Vila is deployable in the data center, cloud and at the edge, including Jetson Orin and laptop by AWQ 4bit quantizati...\" data-rh=\"true\"><meta property=\"og:title\" content=\"nvidia / vila\" data-rh=\"true\"><meta property=\"og:description\" content=\"Vila Model Card Description NVIDIA Vila is a leading vision language model (VLMs) that enables the ability to query and summarize images and video from the physical or virtual world. Vila is deployable in the data center, cloud and at the edge, including Jetson Orin and laptop by AWQ 4bit quantizati...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"nvidia / vila\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Vila Model Card Description NVIDIA Vila is a leading vision language model (VLMs) that enables the ability to query and summarize images and video from the physical or virtual world. Vila is deployable in the data center, cloud and at the edge, including Jetson Orin and laptop by AWQ 4bit quantizati...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20vila&amp;projectTitle=NIM&amp;description=Vila%20Model%20Card%20Description%20NVIDIA%20Vila%20is%20a%20leading%20vision%20language%20model%20(VLMs)%20that%20enables%20the%20ability%20to%20query%20and%20summarize%20images%20and%20video%20from%20the%20physical%20or%20virtual%20world.%20Vila%20is%20deployable%20in%20the%20data%20center%2C%20cloud%20and%20at%20the%20edge%2C%20including%20Jetson%20Orin%20and%20laptop%20by%20AWQ%204bit%20quantizati...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=nvidia%20%2F%20vila&amp;projectTitle=NIM&amp;description=Vila%20Model%20Card%20Description%20NVIDIA%20Vila%20is%20a%20leading%20vision%20language%20model%20(VLMs)%20that%20enables%20the%20ability%20to%20query%20and%20summarize%20images%20and%20video%20from%20the%20physical%20or%20virtual%20world.%20Vila%20is%20deployable%20in%20the%20data%20center%2C%20cloud%20and%20at%20the%20edge%2C%20including%20Jetson%20Orin%20and%20laptop%20by%20AWQ%204bit%20quantizati...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/nvidia-vila\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779464388316\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"https://cdn.readme.i",
    "source": "https://docs.api.nvidia.com/nim/reference/nvidia-vila"
  },
  "openai/gpt-oss-120b": {
    "fetched_at": 1779873825.632829,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"L+NvVGSflKxP+ugq8LrVaA==:cJt6pLRc0viIsQkRnHG4EOIyf1UcrPHPdgOLqO2baFZk3TfbV6V4/tON4xxW1Mol3MRLgdW9oym6/hP9bKBnd076FtX2ePVwYrP1b2fZ5tpzJ61DsK0tQ4Q6gt9/z6Iao2jisL8ij3ehH6ya9nZoyiLiui+Y8C2KvoblG3Y/BPmRcXrOtVFu66ZitJqgigdY\"><meta name=\"readme-version\" content=\"1.0\"><title>openai / gpt-oss-120b</title><meta name=\"description\" content=\"GPT OSS 120B Overview Description: OpenAI releases the gpt-oss family of open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. The family consists of the: gpt-oss-120b \u2014 for production, general purpose, high reasoning use-cases that fits into a single ...\" data-rh=\"true\"><meta property=\"og:title\" content=\"openai / gpt-oss-120b\" data-rh=\"true\"><meta property=\"og:description\" content=\"GPT OSS 120B Overview Description: OpenAI releases the gpt-oss family of open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. The family consists of the: gpt-oss-120b \u2014 for production, general purpose, high reasoning use-cases that fits into a single ...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"openai / gpt-oss-120b\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"GPT OSS 120B Overview Description: OpenAI releases the gpt-oss family of open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. The family consists of the: gpt-oss-120b \u2014 for production, general purpose, high reasoning use-cases that fits into a single ...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=openai%20%2F%20gpt-oss-120b&amp;projectTitle=NIM&amp;description=GPT%20OSS%20120B%20Overview%20Description%3A%20OpenAI%20releases%20the%20gpt-oss%20family%20of%20open-weight%20models%20designed%20for%20powerful%20reasoning%2C%20agentic%20tasks%2C%20and%20versatile%20developer%20use%20cases.%20The%20family%20consists%20of%20the%3A%20gpt-oss-120b%20%E2%80%94%20for%20production%2C%20general%20purpose%2C%20high%20reasoning%20use-cases%20that%20fits%20into%20a%20single%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=openai%20%2F%20gpt-oss-120b&amp;projectTitle=NIM&amp;description=GPT%20OSS%20120B%20Overview%20Description%3A%20OpenAI%20releases%20the%20gpt-oss%20family%20of%20open-weight%20models%20designed%20for%20powerful%20reasoning%2C%20agentic%20tasks%2C%20and%20versatile%20developer%20use%20cases.%20The%20family%20consists%20of%20the%3A%20gpt-oss-120b%20%E2%80%94%20for%20production%2C%20general%20purpose%2C%20high%20reasoning%20use-cases%20that%20fits%20into%20a%20single%20...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/openai-gpt-oss-120b\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\"",
    "source": "https://docs.api.nvidia.com/nim/reference/openai-gpt-oss-120b"
  },
  "openai/gpt-oss-20b": {
    "fetched_at": 1779873825.7884393,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"lAWd8pwqIesMDelZ1wgcqA==:nANI7VgJVb5ef9f+rb9+yyS+goFJcZoeGDMib9GLOBn7K4Ynf7PCSAtydfY/hU4T/gVBQMU61DQLqhb/yPuo/2GoAK9IP4/S0fGPyFElvb9h4eXD7d46/330bdqkZ5f8ro37FYBqcjnhLFudP5CCkw4b0wac/ThoBInqqaVxs894+LcA1b+f/VqWx+Yyddog\"><meta name=\"readme-version\" content=\"1.0\"><title>openai / gpt-oss-20b</title><meta name=\"description\" content=\"GPT OSS 20B Overview Description: OpenAI releases the gpt-oss family of open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. The family consists of the: gpt-oss-120b \u2014 for production, general purpose, high reasoning use-cases that fits into a single H...\" data-rh=\"true\"><meta property=\"og:title\" content=\"openai / gpt-oss-20b\" data-rh=\"true\"><meta property=\"og:description\" content=\"GPT OSS 20B Overview Description: OpenAI releases the gpt-oss family of open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. The family consists of the: gpt-oss-120b \u2014 for production, general purpose, high reasoning use-cases that fits into a single H...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"openai / gpt-oss-20b\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"GPT OSS 20B Overview Description: OpenAI releases the gpt-oss family of open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. The family consists of the: gpt-oss-120b \u2014 for production, general purpose, high reasoning use-cases that fits into a single H...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=openai%20%2F%20gpt-oss-20b&amp;projectTitle=NIM&amp;description=GPT%20OSS%2020B%20Overview%20Description%3A%20OpenAI%20releases%20the%20gpt-oss%20family%20of%20open-weight%20models%20designed%20for%20powerful%20reasoning%2C%20agentic%20tasks%2C%20and%20versatile%20developer%20use%20cases.%20The%20family%20consists%20of%20the%3A%20gpt-oss-120b%20%E2%80%94%20for%20production%2C%20general%20purpose%2C%20high%20reasoning%20use-cases%20that%20fits%20into%20a%20single%20H...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=openai%20%2F%20gpt-oss-20b&amp;projectTitle=NIM&amp;description=GPT%20OSS%2020B%20Overview%20Description%3A%20OpenAI%20releases%20the%20gpt-oss%20family%20of%20open-weight%20models%20designed%20for%20powerful%20reasoning%2C%20agentic%20tasks%2C%20and%20versatile%20developer%20use%20cases.%20The%20family%20consists%20of%20the%3A%20gpt-oss-120b%20%E2%80%94%20for%20production%2C%20general%20purpose%2C%20high%20reasoning%20use-cases%20that%20fits%20into%20a%20single%20H...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/openai-gpt-oss-20b\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"",
    "source": "https://docs.api.nvidia.com/nim/reference/openai-gpt-oss-20b"
  },
  "qwen/qwen3-coder-480b-a35b-instruct": {
    "fetched_at": 1779873825.985518,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"+o4m7KXlNRxI+EjKv2vdag==:CWO3L1EbkwaUD8b0pa1+sStexmKVufH6O9hKAPMadG6qbwzU2Lu8dNFtf1eX3QMm/tIjOycm7e/uBFl+LjCHhNusb9mOoKIX4pBdGQN9pStsgvA+hRvyluSJIfte0AVB5XdpHiLPA837i67WuxNmvptMVuuZfUFk0Menuuxm6jow9npLyGJJe7L1POpLljQg\"><meta name=\"readme-version\" content=\"1.0\"><title>qwen / qwen3-coder-480b-a35b-instruct</title><meta name=\"description\" content=\"Qwen3-Coder-480B-A35B-Instruct Model Overview Description: Qwen3-Coder-480B-A35B-Instruct is a state-of-the-art large language model specifically designed for code generation and agentic coding tasks. It is a mixture-of-experts (MoE) model with 480B total parameters and 35B activated parameters, fea...\" data-rh=\"true\"><meta property=\"og:title\" content=\"qwen / qwen3-coder-480b-a35b-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Qwen3-Coder-480B-A35B-Instruct Model Overview Description: Qwen3-Coder-480B-A35B-Instruct is a state-of-the-art large language model specifically designed for code generation and agentic coding tasks. It is a mixture-of-experts (MoE) model with 480B total parameters and 35B activated parameters, fea...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"qwen / qwen3-coder-480b-a35b-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Qwen3-Coder-480B-A35B-Instruct Model Overview Description: Qwen3-Coder-480B-A35B-Instruct is a state-of-the-art large language model specifically designed for code generation and agentic coding tasks. It is a mixture-of-experts (MoE) model with 480B total parameters and 35B activated parameters, fea...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=qwen%20%2F%20qwen3-coder-480b-a35b-instruct&amp;projectTitle=NIM&amp;description=Qwen3-Coder-480B-A35B-Instruct%20Model%20Overview%20Description%3A%20Qwen3-Coder-480B-A35B-Instruct%20is%20a%20state-of-the-art%20large%20language%20model%20specifically%20designed%20for%20code%20generation%20and%20agentic%20coding%20tasks.%20It%20is%20a%20mixture-of-experts%20(MoE)%20model%20with%20480B%20total%20parameters%20and%2035B%20activated%20parameters%2C%20fea...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=qwen%20%2F%20qwen3-coder-480b-a35b-instruct&amp;projectTitle=NIM&amp;description=Qwen3-Coder-480B-A35B-Instruct%20Model%20Overview%20Description%3A%20Qwen3-Coder-480B-A35B-Instruct%20is%20a%20state-of-the-art%20large%20language%20model%20specifically%20designed%20for%20code%20generation%20and%20agentic%20coding%20tasks.%20It%20is%20a%20mixture-of-experts%20(MoE)%20model%20with%20480B%20total%20parameters%20and%2035B%20activated%20parameters%2C%20fea...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/qwen-qwen3-coder-480b-a35b-instruct\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></scri",
    "source": "https://docs.api.nvidia.com/nim/reference/qwen-qwen3-coder-480b-a35b-instruct"
  },
  "qwen/qwen3-next-80b-a3b-instruct": {
    "fetched_at": 1779873826.0303686,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"J9Isfswo1Ort2ruVvqnGEw==:Mjzj2HU9OUYf9/VYwEwz10at5XLxQCDYBuD89zh+W2cUt6FUWg4HS+jq9bxahJaq5QS5ME4wlKNFaDYJsUHm4VPwwpGWaUDIZ//JU+EwanOZJ5WZyg5cLmw1rwl2d//joEYgdGHk9HYFNOHOZAV0ELoP9Pf4NeqBtDK1sDmB0IDGRbg0DcJgZyVdZixi3CCm\"><meta name=\"readme-version\" content=\"1.0\"><title>qwen / qwen3-next-80b-a3b-instruct</title><meta name=\"description\" content=\"Qwen3-Next-80B-A3B-Instruct Description Qwen3-Next-80B-A3B-Instruct is a causal language model that is instruction-optimized for chat and agent applications. It features a Mixture-of-Experts (MoE) architecture that achieves an extremely low activation ratio, drastically reducing FLOPs per token whil...\" data-rh=\"true\"><meta property=\"og:title\" content=\"qwen / qwen3-next-80b-a3b-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Qwen3-Next-80B-A3B-Instruct Description Qwen3-Next-80B-A3B-Instruct is a causal language model that is instruction-optimized for chat and agent applications. It features a Mixture-of-Experts (MoE) architecture that achieves an extremely low activation ratio, drastically reducing FLOPs per token whil...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"qwen / qwen3-next-80b-a3b-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Qwen3-Next-80B-A3B-Instruct Description Qwen3-Next-80B-A3B-Instruct is a causal language model that is instruction-optimized for chat and agent applications. It features a Mixture-of-Experts (MoE) architecture that achieves an extremely low activation ratio, drastically reducing FLOPs per token whil...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=qwen%20%2F%20qwen3-next-80b-a3b-instruct&amp;projectTitle=NIM&amp;description=Qwen3-Next-80B-A3B-Instruct%20Description%20Qwen3-Next-80B-A3B-Instruct%20is%20a%20causal%20language%20model%20that%20is%20instruction-optimized%20for%20chat%20and%20agent%20applications.%20It%20features%20a%20Mixture-of-Experts%20(MoE)%20architecture%20that%20achieves%20an%20extremely%20low%20activation%20ratio%2C%20drastically%20reducing%20FLOPs%20per%20token%20whil...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=qwen%20%2F%20qwen3-next-80b-a3b-instruct&amp;projectTitle=NIM&amp;description=Qwen3-Next-80B-A3B-Instruct%20Description%20Qwen3-Next-80B-A3B-Instruct%20is%20a%20causal%20language%20model%20that%20is%20instruction-optimized%20for%20chat%20and%20agent%20applications.%20It%20features%20a%20Mixture-of-Experts%20(MoE)%20architecture%20that%20achieves%20an%20extremely%20low%20activation%20ratio%2C%20drastically%20reducing%20FLOPs%20per%20token%20whil...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/qwen-qwen3-next-80b-a3b-instruct\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"F",
    "source": "https://docs.api.nvidia.com/nim/reference/qwen-qwen3-next-80b-a3b-instruct"
  },
  "qwen/qwen3-next-80b-a3b-thinking": {
    "fetched_at": 1779188940.5989919,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.736.0\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"K+S/S/7unr3VTwp0Lb8fPA==:yhrlX1v6Mvec0mcyd5ysJmZx2AqBHLjttFGBq8z1sDPrr/q7++F5N8zCy7EwZknyZUvcga8pppsMF8X1rlk0Bnsz39OaKnYB1+5KRvkzJmdmeXIGw/6v3mlmn66HoWlXX2fiiwqwsn3ozjr6w0CGR+EbW9d5Mx5YEw7QfkiNcIFtFoJnHGnna6F9pS9m77tU\"><meta name=\"readme-version\" content=\"1.0\"><title>qwen / qwen3-next-80b-a3b-thinking</title><meta name=\"description\" content=\"Qwen3-Next-80B-A3B-Thinking Description Qwen3-Next-80B-A3B-Thinking is a part of the Qwen3-Next series that features the following key enchancements: Hybrid Attention : Replaces standard attention with the combination of Gated DeltaNet and Gated Attention , enabling efficient context modeling for ul...\" data-rh=\"true\"><meta property=\"og:title\" content=\"qwen / qwen3-next-80b-a3b-thinking\" data-rh=\"true\"><meta property=\"og:description\" content=\"Qwen3-Next-80B-A3B-Thinking Description Qwen3-Next-80B-A3B-Thinking is a part of the Qwen3-Next series that features the following key enchancements: Hybrid Attention : Replaces standard attention with the combination of Gated DeltaNet and Gated Attention , enabling efficient context modeling for ul...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"qwen / qwen3-next-80b-a3b-thinking\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Qwen3-Next-80B-A3B-Thinking Description Qwen3-Next-80B-A3B-Thinking is a part of the Qwen3-Next series that features the following key enchancements: Hybrid Attention : Replaces standard attention with the combination of Gated DeltaNet and Gated Attention , enabling efficient context modeling for ul...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=qwen%20%2F%20qwen3-next-80b-a3b-thinking&amp;projectTitle=NIM&amp;description=Qwen3-Next-80B-A3B-Thinking%20Description%20Qwen3-Next-80B-A3B-Thinking%20is%20a%20part%20of%20the%20Qwen3-Next%20series%20that%20features%20the%20following%20key%20enchancements%3A%20Hybrid%20Attention%20%3A%20Replaces%20standard%20attention%20with%20the%20combination%20of%20Gated%20DeltaNet%20and%20Gated%20Attention%20%2C%20enabling%20efficient%20context%20modeling%20for%20ul...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=qwen%20%2F%20qwen3-next-80b-a3b-thinking&amp;projectTitle=NIM&amp;description=Qwen3-Next-80B-A3B-Thinking%20Description%20Qwen3-Next-80B-A3B-Thinking%20is%20a%20part%20of%20the%20Qwen3-Next%20series%20that%20features%20the%20following%20key%20enchancements%3A%20Hybrid%20Attention%20%3A%20Replaces%20standard%20attention%20with%20the%20combination%20of%20Gated%20DeltaNet%20and%20Gated%20Attention%20%2C%20enabling%20efficient%20context%20modeling%20for%20ul...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/qwen-qwen3-next-80b-a3b-thinking\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779118827077\"></script",
    "source": "https://docs.api.nvidia.com/nim/reference/qwen-qwen3-next-80b-a3b-thinking"
  },
  "sarvamai/sarvam-m": {
    "fetched_at": 1779873826.1251073,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"T5wp6TzRf1hNyMQJv/2oIA==:8CV07Xfp2TF2mLwi8/A3w1RLcVhNu0i9JNu/NSchOg0eZhZPgw/1MfrrdlAL8jIqWpsunCv0YIR6gBwesKZClQFqhN7QCY/lhAX1dTCjpJIfnHNsFJT6KijrMJqUxtJzBEc7k2OQeifEAsN6qawu/CXTY5lGC4lz92JtK5efvsxiLeA8XShA18xJ/8y+SfT5\"><meta name=\"readme-version\" content=\"1.0\"><title>sarvamai / sarvam-m</title><meta name=\"description\" content=\"Sarvam-m Overview Description Sarvam-m generates human-like text for a seamless chatting experience, providing a smooth and accessible multilingual conversation experience, and is intended for general-purpose conversation and text generation tasks. This model is ready for commercial/non-commercial u...\" data-rh=\"true\"><meta property=\"og:title\" content=\"sarvamai / sarvam-m\" data-rh=\"true\"><meta property=\"og:description\" content=\"Sarvam-m Overview Description Sarvam-m generates human-like text for a seamless chatting experience, providing a smooth and accessible multilingual conversation experience, and is intended for general-purpose conversation and text generation tasks. This model is ready for commercial/non-commercial u...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"sarvamai / sarvam-m\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Sarvam-m Overview Description Sarvam-m generates human-like text for a seamless chatting experience, providing a smooth and accessible multilingual conversation experience, and is intended for general-purpose conversation and text generation tasks. This model is ready for commercial/non-commercial u...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=sarvamai%20%2F%20sarvam-m&amp;projectTitle=NIM&amp;description=Sarvam-m%20Overview%20Description%20Sarvam-m%20generates%20human-like%20text%20for%20a%20seamless%20chatting%20experience%2C%20providing%20a%20smooth%20and%20accessible%20multilingual%20conversation%20experience%2C%20and%20is%20intended%20for%20general-purpose%20conversation%20and%20text%20generation%20tasks.%20This%20model%20is%20ready%20for%20commercial%2Fnon-commercial%20u...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=sarvamai%20%2F%20sarvam-m&amp;projectTitle=NIM&amp;description=Sarvam-m%20Overview%20Description%20Sarvam-m%20generates%20human-like%20text%20for%20a%20seamless%20chatting%20experience%2C%20providing%20a%20smooth%20and%20accessible%20multilingual%20conversation%20experience%2C%20and%20is%20intended%20for%20general-purpose%20conversation%20and%20text%20generation%20tasks.%20This%20model%20is%20ready%20for%20commercial%2Fnon-commercial%20u...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/sarvamai-sarvam-m\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"https://cdn.readme.io/public/hub/web",
    "source": "https://docs.api.nvidia.com/nim/reference/sarvamai-sarvam-m"
  },
  "snowflake/arctic-embed-l": {
    "fetched_at": 1779873826.3515463,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"GK1guegcx1p3tVy/3Zq4nQ==:gzKWGmB6b/a2ZutFLmUhF+PbAXLh4LEqarXm9xp28OEgoi3QHh7pMr7LnfKsKVcoOyjZKNZsiieJ8Bj19d+RzwiwES1yyUduGO5VAzG+KPQdTfH1vub3OH31VDS04ts8TDV+9sXPmuy66F9GOmQNiSFzYwpSzYrMJ+M/RNGd45wSFC2m2qTHPLny7CeviY4w\"><meta name=\"readme-version\" content=\"1.0\"><title>snowflake / arctic-embed-l</title><meta name=\"description\" content=\"Model Overview Description snowflake-arctic-embed is a suite of text embedding models that creates high-quality retrieval models optimized for performance. These models are ready for commercial use free-of-charge. The snowflake-arctic-embedding models achieve state-of-the-art performance on the MTEB...\" data-rh=\"true\"><meta property=\"og:title\" content=\"snowflake / arctic-embed-l\" data-rh=\"true\"><meta property=\"og:description\" content=\"Model Overview Description snowflake-arctic-embed is a suite of text embedding models that creates high-quality retrieval models optimized for performance. These models are ready for commercial use free-of-charge. The snowflake-arctic-embedding models achieve state-of-the-art performance on the MTEB...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"snowflake / arctic-embed-l\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Model Overview Description snowflake-arctic-embed is a suite of text embedding models that creates high-quality retrieval models optimized for performance. These models are ready for commercial use free-of-charge. The snowflake-arctic-embedding models achieve state-of-the-art performance on the MTEB...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=snowflake%20%2F%20arctic-embed-l&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20snowflake-arctic-embed%20is%20a%20suite%20of%20text%20embedding%20models%20that%20creates%20high-quality%20retrieval%20models%20optimized%20for%20performance.%20These%20models%20are%20ready%20for%20commercial%20use%20free-of-charge.%20The%20snowflake-arctic-embedding%20models%20achieve%20state-of-the-art%20performance%20on%20the%20MTEB...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=snowflake%20%2F%20arctic-embed-l&amp;projectTitle=NIM&amp;description=Model%20Overview%20Description%20snowflake-arctic-embed%20is%20a%20suite%20of%20text%20embedding%20models%20that%20creates%20high-quality%20retrieval%20models%20optimized%20for%20performance.%20These%20models%20are%20ready%20for%20commercial%20use%20free-of-charge.%20The%20snowflake-arctic-embedding%20models%20achieve%20state-of-the-art%20performance%20on%20the%20MTEB...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/snowflake-arctic-embed-l\"><script src=\"https://cdn.readme.io/public/js/cash-dom.min.js?1779831901460\"></script><link data-chunk=\"Footer\" rel=\"preload\" as=\"style\" href=\"https://cd",
    "source": "https://docs.api.nvidia.com/nim/reference/snowflake-arctic-embed-l"
  },
  "stockmark/stockmark-2-100b-instruct": {
    "fetched_at": 1779873826.5757878,
    "raw": "<!DOCTYPE html><html lang=\"en\" style=\"\" data-color-mode=\"dark\" class=\" useReactApp isRefPage \"><head><meta charset=\"utf-8\"><meta name=\"readme-deploy\" content=\"5.746.2\"><meta name=\"readme-subdomain\" content=\"nim\"><meta name=\"readme-repo\" content=\"nim-d8c8c60d2d4f\"><meta name=\"readme-basepath-childProject\" content=\"nim\"><meta name=\"readme-project-flags\" content=\"38SZDoEBqMrFQu9YcVVpzg==:QvmT8x7TonabyHW5qWw5BdR9h6rPdRHpNgr6DbfRR7OIdx0CyR0NZWwUFIGL/PW+UWDCxy7R7cEKv56sgMaTO7oSY0bdQ5NyHkY4EY1/yL9286H3R9pKwUqxKE/RfHVO4jm3GP5XeriSzBjXIuEFzvRbjKSCG+V2NnEX1NJO+gF69hVQwHw6J60Y+UdQoZQf\"><meta name=\"readme-version\" content=\"1.0\"><title>stockmark / stockmark-2-100b-instruct</title><meta name=\"description\" content=\"Stockmark-2-100B-Instruct Description Stockmark-2-100B-Instruct is a 100-billion-parameter large language model built from scratch, with a particular focus on Japanese. It was pre-trained on approximately 2.0 trillion tokens of data, consisting of 60% English, 30% Japanese, and 10% code. Following p...\" data-rh=\"true\"><meta property=\"og:title\" content=\"stockmark / stockmark-2-100b-instruct\" data-rh=\"true\"><meta property=\"og:description\" content=\"Stockmark-2-100B-Instruct Description Stockmark-2-100B-Instruct is a 100-billion-parameter large language model built from scratch, with a particular focus on Japanese. It was pre-trained on approximately 2.0 trillion tokens of data, consisting of 60% English, 30% Japanese, and 10% code. Following p...\" data-rh=\"true\"><meta property=\"og:site_name\" content=\"NIM\"><meta name=\"twitter:title\" content=\"stockmark / stockmark-2-100b-instruct\" data-rh=\"true\"><meta name=\"twitter:description\" content=\"Stockmark-2-100B-Instruct Description Stockmark-2-100B-Instruct is a 100-billion-parameter large language model built from scratch, with a particular focus on Japanese. It was pre-trained on approximately 2.0 trillion tokens of data, consisting of 60% English, 30% Japanese, and 10% code. Following p...\" data-rh=\"true\"><meta name=\"twitter:card\" content=\"summary_large_image\"><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"><meta property=\"og:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=stockmark%20%2F%20stockmark-2-100b-instruct&amp;projectTitle=NIM&amp;description=Stockmark-2-100B-Instruct%20Description%20Stockmark-2-100B-Instruct%20is%20a%20100-billion-parameter%20large%20language%20model%20built%20from%20scratch%2C%20with%20a%20particular%20focus%20on%20Japanese.%20It%20was%20pre-trained%20on%20approximately%202.0%20trillion%20tokens%20of%20data%2C%20consisting%20of%2060%25%20English%2C%2030%25%20Japanese%2C%20and%2010%25%20code.%20Following%20p...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta name=\"twitter:image\" content=\"https://cdn.readme.io/og-image/create?type=reference&amp;title=stockmark%20%2F%20stockmark-2-100b-instruct&amp;projectTitle=NIM&amp;description=Stockmark-2-100B-Instruct%20Description%20Stockmark-2-100B-Instruct%20is%20a%20100-billion-parameter%20large%20language%20model%20built%20from%20scratch%2C%20with%20a%20particular%20focus%20on%20Japanese.%20It%20was%20pre-trained%20on%20approximately%202.0%20trillion%20tokens%20of%20data%2C%20consisting%20of%2060%25%20English%2C%2030%25%20Japanese%2C%20and%2010%25%20code.%20Following%20p...&amp;logoUrl=https%3A%2F%2Ffiles.readme.io%2F9294124135914fb6f7626bb3920389713ffaefcb0df8c379cc098cf03ed6796e-small-NVIDIA_Logo_For_LightBG.png&amp;color=%23000000&amp;variant=light\" data-rh=\"true\"><meta property=\"og:image:width\" content=\"1200\"><meta property=\"og:image:height\" content=\"630\"><link id=\"favicon\" rel=\"shortcut icon\" href=\"https://files.readme.io/787355f-favicon.ico\" type=\"image/x-icon\"><link rel=\"canonical\" href=\"https://docs.api.nvidia.com/nim/reference/stockmark-stockmark-2-100b-instruct\"><script src=\"https://cdn.readme.io/public/js/c",
    "source": "https://docs.api.nvidia.com/nim/reference/stockmark-stockmark-2-100b-instruct"
  }
}