Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Pulse
99
Velocity
+334%
Stars
5,699
Native MLX runtime for typed decision models on Apple Silicon, 7ms inference.
Fast, local inference for typed decision models using Apple's MLX framework.
Achieve 7ms inference for typed decisions on your M3 Max, no cloud needed.
Why Trending
Natively runs typed decision models on Apple Silicon with extremely low latency.
Target Audience
Developers on Apple Silicon needing fast local inference.
Similar Projects