Ministral-3: Canceled desc =

[markuman]

LocalAI version:

3.8.0

Environment, CPU architecture, OS, and Version:

Linux fw 6.17.12-1-MANJARO #1 SMP PREEMPT_DYNAMIC Fri, 12 Dec 2025 19:42:49 +0000 x86_64 GNU/Linux

Describe the bug

I load https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512-GGUF/resolve/main/Ministral-3-3B-Instruct-2512-Q5_K_M.gguf via http://localhost:8080/import-model and just try to run a chat afterwards.

To Reproduce

Expected behavior

Logs

4:51PM INF BackendLoader starting backend=llama-cpp modelID=Ministral-3-3B-Instruct-2512-Q5_K_M.gguf o.model=Ministral-3-3B-Instruct-2512-Q5_K_M.gguf
4:51PM ERR Failed to load model Ministral-3-3B-Instruct-2512-Q5_K_M.gguf with backend llama-cpp error="failed to load model with internal loader: could not load model: rpc error: code = Canceled desc = " modelID=Ministral-3-3B-Instruct-2512-Q5_K_M.gguf
4:51PM ERR Stream ended with error: failed to load model with internal loader: could not load model: rpc error: code = Canceled desc = 
4:51PM INF HTTP request method=POST path=/v1/chat/completions status=200

Additional context