Laya MLX | Hacker News - But Better

Laya MLX github.com

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

3 points•blueaquilae•10 days ago•1 comment•

#mlx #laya #laya mlx #runtime #typed #max #native #short

1 comment

blueaquilae10 days ago

Native MLX runtime for Laya typed decision models

Read the full thread on Hacker News →

Related stories

Laya-mlx and 12 more trending open-source AI repos · week 39, 2026
Hacker News · 1 points · 7 days ago
Ask HN: React Native or Flutter when the back end is Node?
Hacker News · 5 points · 2 days ago
Show HN: Clx 0.4.0 – native compiler for Luasamyeyo.github.io
Hacker News · 2 points · 1 day ago
Show HN: Peekaboolean – image and jev-like typed questions in typed anwers outgithub.com
Hacker News · 2 points · 4 days ago
Show HN: InstinctFlash – High-Performance Serving Runtime for Robotics Modelsgithub.com
Hacker News · 27 points · 8 days ago
Laya Studio: Specialize Laya Without Fine-Tuninggithub.com
Hacker News · 1 points · 5 days ago