laya-mlx / laya-coreml: Laya on Apple Silicon

Native MLX and Core ML runtimes for Laya typed decisions: `pip install 'laya-mlx[demo]'`, no text generation, no PyTorch, no cloud API. A Rubik's-cube demo runs 100 moves locally.

Notes

7–14 ms short decisions on an M3 Max (MLX) and ~5 ms on Core ML / Neural Engine, per the repositories' benchmarks.

source-backed — Public repository, docs or live artifact. About this label

Destinations

Also linked

• laya-coreml ↗

Filed under

• #local
• #mlx
• #coreml
• #macos
• #replica

In collections

• Local & replica models →