RUNTIME / MEDIUM
MLX LM
Native Apple silicon inference, experimentation and fine-tuning
一手來源DifficultyMediumSetup profile
Platforms1apple
APIPython server and CLI
01 / INSTALL & RUN
- 1Install
pip install mlx-lm - 2Start a model
mlx_lm.chat --model google/gemma-3-1b-it - 3Connect your app
Python server and CLI. Keep the service bound to localhost unless you add authentication and network controls.
注意
Only for Apple silicon. Use an MLX-converted model and tune KV cache size for long contexts.
02 / COMPATIBLE MODELS