ml-explore/mlx-lm
Run LLMs with MLX
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
3 releases in the last 90 days, the latest 20 days ago, with 266 contributors on GitHub.
Peaked at #23 in the weekly ranking the week of Sep 14, its best in the past year.
Use Cases & Benefits
- Run and fine-tune large language models on Apple silicon using a Python package integrated with Hugging Face Hub.
- Enables efficient model quantization, distributed inference, and prompt caching to optimize performance on Apple hardware.
- Use for generating text or chatting interactively with LLMs via command line or Python API on Apple silicon devices.
- Use for quantizing and uploading custom or pre-trained models to Hugging Face Hub with built-in conversion tools.
- Use for scaling long prompt handling and multi-turn dialogues with prompt caching and rotating key-value cache support.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
MLX LM is a Python package for generating text and fine-tuning large language models on Apple silicon with MLX.
This will give you a chat REPL that you can use to interact with the LLM. The chat context is preserved during the lifetime of the REPL.
To see a description of all the arguments you can do:
Check out the generation example to see how to use the API in more detail.
The
mlx-lmpackage also comes with functionality to quantize and optionally upload models to the Hugging Face Hub.You can convert models using the Python API:
This will generate a 4-bit quantized Mistral 7B and upload it to the repo
mlx-community/My-Mistral-7B-Instruct-v0.3-4bit. It will also save the converted model in the pathmlx_modelby default.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+984 stars over 86 days across 8 snapshot days; best day +16 on Aug 20.
Forks
1.2K+222
Open issues
267-355
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/skills | 187.8K | +2.9K | 15 | — |
| DuarteSantos8/openGym | 19.7K | +2.4K | 60 | 2 days ago |
| shiyu-coder/Kronos | 47.0K | +2.3K | 16 | — |
| NationalSecurityAgency/ghidra | 98.2K | +2.3K | 64 | 14 days ago |
| microsoft/VibeVoice | 56.0K | +1.1K | 29 | — |
| ml-explore/mlx-lm | 7.6K | — | 64 | 20 days ago |
| Category median | 56.0K | +2.3K | 29 | — |
Also by ml-explore
Other repositories from this maintainer that GStars tracks
Discover Repositories
Search across tracked repositories by name or description