⬢github Python · 1.5K ★ · pushed 4 d ago · Apache-2.0
mizorewww/laya-coreml
Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.
Laya-CoreML runs the Laya typed-decision model entirely on-device on Apple Silicon via Core ML and the Neural Engine, returning calibrated probabilities for multiple-choice, score, and boolean questions with no token generation. It includes a local Snake game demo, a Python API, and reproducible latency and energy benchmarks (~5 ms per short decision on M3 Max).
Why now: It's trending as a newly popular repo showcasing validated on-device inference with notable energy-efficiency wins over MLX, though the authors note the claimed 10x speedup was not achieved.
Who it is for: macOS/Apple Silicon developers building fast, private, local classification or decision features without LLM token generation.
apple-neural-engineapple-siliconcoremldecision-modellayalocal-aimodernberton-device-aityped-decisions
Stars over our 10 snapshots: 1.5K to 1.5K, since 1 h ago.
Where people talked about it
- ⬢github new repos, most starred just now
API: https://socialmediatrends-api.osmike.com/v1/repos/mizorewww/laya-coreml