mlx-lm runs language models from Hugging Face with Apple's MLX. It can generate and chat, convert and quantize models and upload them, fine-tune them with LoRA or in full, and serve a basic OpenAI-style endpoint.
It runs on Apple silicon. It's built on MLX, which needs macOS 14.0 or later and a native Python 3.10 or newer. Thousands of ready-converted models are in the mlx-community organisation on Hugging Face.
It's free and open source (MIT) and runs on your Mac.
How to Get It
Official downloads only. MLX never re-hosts an app, and never runs a command for you.
MLX Score
Ranked against the run models locally listings, from real public data only. How the score works.
Pairs Well With
Hugging Face CLI (hf)Dev toolsInformation
- Developer
- Apple (ml-explore)
- Category
- Run models locally
- Price
- Free
- Your data
- Runs on your Mac
- Licence
- MIT
- Mac
- macOS 14.0 or later
- iPhone and iPad
- —
- Needs
- M1 or later
- Links
- Website · GitHub · Hugging Face
- Facts checked
- 2026-11-01
Sources
Compare
You Might Also Like
OllamaRun locally
llama.cppRun locally
LM StudioRun locally
Open WebUIRun locally
AnythingLLMRun locally
exoRun locally
LlamaRun locally
vMLX (MLX Studio)Run locallymlx-lm is a product of Apple (ml-explore); MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.