All projects

laya-mlx

mizorewww/laya-mlx

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

Open-source alternativesPython
Stars
6,172
Forks
473

Review source

View cited source

Topics

apple-silicondecision-modelinferencelayalocal-aimachine-learningmlxmodernbert