Library / SDK
Inference & Serving
MLX LM
1Run 2LLMs 3on 4Apple 5silicon 6fast.
the six Ws · specification
W1
Who
By Apple.
W2
What
Tools to run and fine-tune language models on Apple silicon with MLX.
W3
Where
A Python package on Apple hardware.
W4
When
When running models on a Mac.
W5
Why
Native, efficient inference on Apple chips.
W6
With
Python and Apple silicon.
W7
Watch
MIT, from Apple; runs entirely on your Mac, no credentials.
AppleMLXOn-device