lmstudio-ai / lmstudio-ai/mlx-engine
it doesn't seem to support 1bit
Open
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 133
- Avg merge
- 21h 6m
- Merged PRs (30d)
- 1
Description
```
🥲 Failed to load the model
Failed to load model.
Error when loading model: ValueError: [quantize] The requested number of bits 1 is not supported. The supported bits are 2, 3, 4, 5, 6 and 8.
```
Contributor guide
Research direction
Start by tracing the quantization path identified as [quantize] in the loading error and find where the supported bit values are defined. Check how 1-bit models are represented and loaded, then verify the reported model loads successfully with 1-bit quantization without regressing the existing supported bit sizes.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100