simonw / simonw/llm

After `uv tool upgrade llm`, llm Error: 'Unknown model: mlx-community/gemma-3-27b-it-qat-4bit'

Open
#984 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
12.5k
Forks
998
Avg merge
3d 13h
Merged PRs (30d)
10

Description

Ran llm version 0.24.2 on M1 Pro for the last month joyfully. Thanks!

This morning:

uv tool upgrade llm
llm --version
llm, version 0.25
llm                                          
Error: 'Unknown model: mlx-community/gemma-3-27b-it-qat-4bit'
llm models | grep mlx
Default: mlx-community/gemma-3-27b-it-qat-4bit

After uv tool upgrade llm, models are orphaned.

Not sure how to resolve? I'll try to reinstall the model, or perhaps another uninstalled model to test the infra connecting the llm python tool to its underlying model data.

Thanks again!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the upgrade from llm 0.24.2 to 0.25 with the recorded uv and llm commands, then inspect how the configured mlx-community/gemma-3-27b-it-qat-4bit model is discovered after upgrading. Done means an upgraded installation can recognize the configured model, or reports a clear recovery path instead of treating it as orphaned.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, cli
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.