RUNTIME / MEDIUM

MLX LM

Native Apple silicon inference, experimentation and fine-tuning

DifficultyMediumSetup profile

Platforms1apple

APIPython server and CLI

01 / INSTALL & RUN

1
Installpip install mlx-lm
2
Start a modelmlx_lm.chat --model google/gemma-3-1b-it
3
Connect your app
Python server and CLI. Keep the service bound to localhost unless you add authentication and network controls.

Achtung

Only for Apple silicon. Use an MLX-converted model and tune KV cache size for long contexts.

02 / COMPATIBLE MODELS

Repräsentative Open-Weight-Modelle