laya-mlx
by mizorewww
Laya-MLX is a native runtime for decision models, providing fast inference on Apple Silicon, with minimal latency and no cloud dependency.
New and promisingUnder two months old. Expect rough edges and fast changes.
- Stars
- 7k +189 a day, est.
- Licence
- Apache-2.0
- Runs on
- A small server
- Setup
- Moderate
- Language
- Python
- Age
- 37 days
What you can do with it
- Run decision models locally on Apple Silicon
- Perform fast inference for typed decisions
- Use pre-trained models for various decision tasks
Ways a business could use it
- Automate customer service responses
- Implement real-time decision-making in applications
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install via pip and load models using Python code
Follow the official instructions in the project README.
Checked 26 Oct 2026. Summary drafted by AI from the project's README.
