`POST /api/v1/local-ai/llm`: copies a GGUF file into the models folder and makes it the `local` backend.
POST/api/v1/local-ai/llm
The copy runs in its own task, so a client that stops waiting does not leave half a model in the folder.
Request
Responses
- 200
- 400
Where the model is stored
No such file, or not a GGUF file