Skip to main content
MLX is a NumPy-like array framework designed for efficient and flexible machine learning on Apple silicon, brought to you by Apple machine learning research.

​
Installation and Setup

Install several Python packages: 
pip install mlx-lm transformers huggingface_hub

​
Chat models

See a usage example. 
from langchain_community.chat_models.mlx import ChatMLX

​
LLMs

​
MLX Local Pipelines

See a usage example. 
from langchain_community.llms.mlx_pipeline import MLXPipeline
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I