关于本地调用ollama报错问题请求指导

[hyg1998]

下载ollam 并启动本地服务后，勾选 translate api 选择ollama 选择模型名称 启动后 一直报错能看看是什么原因吗
1、本地shell命令显示内容
https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-09-04T09:43:49.951+08:00 level=INFO source=images.go:477 msg="total blobs: 0"
time=2025-09-04T09:43:49.952+08:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
time=2025-09-04T09:43:49.953+08:00 level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.8)"
time=2025-09-04T09:43:49.953+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-09-04T09:43:49.954+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-09-04T09:43:49.954+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=8 efficiency=0 threads=16
time=2025-09-04T09:43:50.174+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-65142d1d-2330-9889-f0e6-e8a28aa815f4 library=cuda variant=v12 compute=8.6 driver=12.1 name="NVIDIA GeForce RTX 3060 Laptop GPU" total="6.0 GiB" available="5.0 GiB"
time=2025-09-04T09:43:50.174+08:00 level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="6.0 GiB" threshold="20.0 GiB"
[GIN] 2025/09/04 - 09:47:38 | 404 | 2.3587ms | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/09/04 - 09:47:38 | 404 | 708.9µs | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/09/04 - 09:47:38 | 404 | 720.8µs | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/09/04 - 09:47:38 | 404 | 1.0283ms | 127.0.0.1 | POST "/api/chat"

2、软件内部日志报错内容

[ERROR] Translation Failed: HTTPError -NotFound

[jiangtaodoudou]

我也是。从来没有成功过，换了最小的qwen模型依然超时。