lmstudio-ai / lmstudio-ai/mlx-engine

Failed to load `IQuest-Coder-V1-40B-Loop-Instruct-4bit` in LMStudio

Open
#257 1 comment 5 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.2k
Forks
133
Avg merge
21h 6m
Merged PRs (30d)
1

Description

Hi!

I can't load mlx-community/IQuest-Coder-V1-40B-Loop-Instruct-4bit in LM Studio:

2026-01-10 13:47:25 [DEBUG]
 [model_kit][INFO]: Loading model from /Users/dd_bb/.lmstudio/models/mlx-community/IQuest-Coder-V1-40B-Loop-Instruct-4bit...
2026-01-10 13:47:25 [DEBUG]
 ValueError: Model type iquestloopcoder not supported.

At:
  /Users/dd_bb/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@9/lib/python3.11/site-packages/mlx_lm/utils.py(75): _get_classes
  /Users/dd_bb/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@9/lib/python3.11/site-packages/mlx_lm/utils.py(210): load_model
  /Users/dd_bb/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@9/lib/python3.11/site-packages/mlx_lm/utils.py(331): load
  /Users/dd_bb/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@9/lib/python3.11/site-packages/mlx_engine/model_kit/model_kit.py(93): _full_model_init
  /Users/dd_bb/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@9/lib/python3.11/site-packages/mlx_engine/model_kit/model_kit.py(128): __init__
  /Users/dd_bb/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@9/lib/python3.11/site-packages/mlx_engine/generate.py(115): load_model
2026-01-10 13:47:25 [DEBUG]
 lmstudio-llama-cpp: failed to load model. Error: Error when loading model: ValueError: Model type iquestloopcoder not supported.

Runtime: LM Studio MLX v0.41.0

MLX version info:
- mlx-engine==0ce04aa
- mlx==0.30.1
- mlx-lm==0.30.0
- mlx-vlm==0.3.10

According to mlx-lm authors, mlx-engine needs to be updated for this models to work.

Thanks!

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 reviewing the mlx-engine model-loading path referenced in the traceback and the linked mlx-lm issue 752. Check how the iquestloopcoder model type is handled by the reported mlx-lm and mlx-engine versions; done means the linked model loads successfully in LM Studio without the unsupported-model error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.