chore(model gallery): 🤖 add 1 new models via gallery agent

gallery/index.yaml

@@ -3295,7 +3295,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -3313,7 +3313,7 @@
   description: |
     google/gemma-3-12b-it is an open-source, state-of-the-art, lightweight, multimodal model built from the same research and technology used to create the Gemini models. It is capable of handling text and image input and generating text output. It has a large context window of 128K tokens and supports over 140 languages. The 12B variant has been fine-tuned using the instruction-tuning approach. Gemma 3 models are suitable for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes them deployable in environments with limited resources such as laptops, desktops, or your own cloud infrastructure.
   overrides:
     #mmproj: gemma-3-12b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-12b-it-Q4_K_M.gguf
   files:
@@ -3331,7 +3331,7 @@
   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-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. Gemma-3-4b-it is a 4 billion parameter model.
   overrides:
     #mmproj: gemma-3-4b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-4b-it-Q4_K_M.gguf
   files:
@@ -6949,7 +6949,7 @@
       sha256: 2756551de7d8ff7093c2c5eec1cd00f1868bc128433af53f5a8d434091d4eb5a
       uri: huggingface://Triangle104/Nano_Imp_1B-Q8_0-GGUF/nano_imp_1b-q8_0.gguf
 - &qwen25
   name: "qwen2.5-14b-instruct" ## Qwen2.5
   icon: https://avatars.githubusercontent.com/u/141221163
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
   license: apache-2.0
@@ -23049,3 +23049,32 @@
     - filename: YanoljaNEXT-Rosetta-27B-2511.i1-Q4_K_M.gguf
       sha256: 0a599099e93ad521045e17d82365a73c1738fff0603d6cb2c9557e96fbc907cb
       uri: huggingface://mradermacher/YanoljaNEXT-Rosetta-27B-2511-i1-GGUF/YanoljaNEXT-Rosetta-27B-2511.i1-Q4_K_M.gguf
+- !!merge <<: *llama3
+  name: "kimi-k2-base-i1"
+  urls:
+    - https://huggingface.co/mradermacher/Kimi-K2-Base-i1-GGUF
+  description: |
+    **Kimi-K2-Base** is a state-of-the-art **Mixture-of-Experts (MoE)** language model developed by Moonshot AI, featuring **1 trillion total parameters** with **32 billion activated parameters** per token. Designed for high-performance reasoning, coding, and agentic tasks, it leverages a novel **MuonClip optimizer** and **MLA attention mechanism** for scalable training and exceptional efficiency.
+
+    ### Key Features:
+    - **Architecture**: Mixture-of-Experts (MoE) with 384 total experts and 8 selected per token.
+    - **Context Length**: Up to **128K tokens**, enabling long-form reasoning and document processing.
+    - **Capabilities**: Strong performance in coding (SWE-bench, LiveCodeBench), math (MATH, AIME), tool use (AceBench, Tau2), and general knowledge (MMLU, MMLU-Pro).
+    - **Base Model**: Ideal for researchers and developers seeking full control for fine-tuning and custom agent development.
+
+    ### Performance Highlights:
+    - **SWE-bench Verified (Agentic Coding)**: 71.6% pass@1 (multiple attempts).
+    - **MMLU (General Knowledge)**: 87.8% accuracy (5-shot).
+    - **MATH Benchmark**: 70.2% pass@1.
+    - **Chinese Evaluation (C-Eval)**: 92.5% accuracy.
+
+    Available on Hugging Face under the **Modified MIT License**. Recommended for deployment with **vLLM**, **SGLang**, or **TensorRT-LLM**.
+
+    > **Note**: This is the *original base model*. The GGUF version (e.g., `mradermacher/Kimi-K2-Base-i1-GGUF`) is a quantized derivative by a third party and not maintained by Moonshot AI. For the official, full-precision model, use [`moonshotai/Kimi-K2-Base`](https://huggingface.co/moonshotai/Kimi-K2-Base).
+  overrides:
+    parameters:
+      model: Kimi-K2-Base.i1-Q4_K_M.gguf.part01of13
+  files:
+    - filename: Kimi-K2-Base.i1-Q4_K_M.gguf.part01of13
+      sha256: a48ed53274228ed818c7369e63dfc7416d91d3b898beef5618d80d03915ee24f
+      uri: huggingface://mradermacher/Kimi-K2-Base-i1-GGUF/Kimi-K2-Base.i1-Q4_K_M.gguf.part01of13