Repository
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.
Stars
7k
Today
+11
last 24 hours
This week
+11
Forks
568
Clone
git clone https://github.com/mizorewww/laya-mlx.gitStar growth
#apple-silicon#inference#machine-learning#mlx#modernbert#decision-model#laya#local-ai#system-one#typed-decisions
- Created
- 2026-09-19
- Last commit
- 2026-10-10
- Gained since tracking
- +11
Updated Sun, 18 Oct 2026 15:32:30 GMT · description from the project itself