MLX LM

by Apple (ml-explore)

Apple's Python package to generate text and fine-tune LLMs, optimized for Apple Silicon.

7,270 stars GitHub MIT Free when localLocalOpen sourceOpen weights

View on GitHub →

What it does

Thousands of Hugging Face models with one command
Model quantization and conversion
LoRA fine-tuning, even on quantized models

Install it

Requirements: An Apple Silicon Mac and Python.

Install

pip install mlx-lm

Chat with a model

mlx_lm.chat

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install MLX LM (https://github.com/ml-explore/mlx-lm) on my machine.
1. Check the requirements: An Apple Silicon Mac and Python. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Install: pip install mlx-lm
- Chat with a model: mlx_lm.chat
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.