Escribe para buscar…

MLX

MLX is a NumPy-like array framework designed for efficient and flexible machine learning on Apple silicon.

Esta página todavía no se ha traducido — se muestra en su idioma original:English
  • https://mlx-framework.org
  • https://ml-explore.github.io/mlx/build/html/index.html

Arrays in MLX live in shared memory. Operations on MLX arrays can be performed on any of the supported device types without performing data copies.

shell
uv tool install mlx
uv tool install mlx-lm
  • https://huggingface.co/mlx-community
shell
mlx_lm.generate --model mlx-community/Qwen3-4B-Instruct-2507-4bit --prompt "hello"

mlx-community/Qwen3-Coder-32B-A3B-4bit

Opencode

mlx_lm.server