{"id":742,"kind":"story","title":"Performance and Usage of the Open-Type Decision AI Model Laya-MLX Running Locally on Apple Silicon","url":"https://github.com/mizorewww/laya-mlx","host":"github.com","by":"startupxo","score":0,"comments":0,"time":"2026-10-02T04:35:07.241Z","origin":"curated","language":{"source":"ko","reading":"en","translated":true},"summary":["Laya-MLX is a local AI model running on Apple Silicon that instantly produces decision results by choosing answers or scoring among options for input sentences.","This model operates on a proprietary MLX runtime without PyTorch or cloud support and can be easily installed and used in Python via code 공개 on GitHub.","Based on the M3 Max chip, it records median latencies of 13.4 ms for single question processing and 7.4 ms for multilingual models, with a max throughput of 146.8~395 per second when processing batches of 64 (Presented by mizorewww, Test environment: M3 Max, macOS 27.2, Python 3.12.13).","The original checkpoints and FP16 converted weights are 공개 on GitHub and Hugging Face, offering three main models suitable for English and multilingual input."],"discussion":"https://startupxo.com/en/742/","markdown":"https://startupxo.com/en/742.md","api":"https://startupxo.com/api/v1/item.json?id=742&lang=en","text":null,"edited":null,"sources":[{"site":"github","name":"GitHub","url":"https://github.com/mizorewww/laya-mlx","score":6699,"comments":null,"observed_at":"2026-10-02T08:37:02Z"}],"thread":[]}