trymirai/uzu

A high-performance inference engine for AI models

59
/ 100
Established

This project helps developers and engineers integrate and run large AI models efficiently on Apple devices. It takes pre-trained AI models, often converted from other formats, and allows them to be executed at high speed, producing predictions or generated content. It's designed for those building applications that need to embed powerful AI capabilities directly into macOS or iOS environments.

1,492 stars. Actively maintained with 77 commits in the last 30 days.

Use this if you are developing AI-powered applications for Apple hardware and need to execute large language models or other AI models quickly and reliably on-device.

Not ideal if you are looking for a cloud-based AI inference solution or if your primary development environment is not Apple Silicon.

on-device-AI machine-learning-deployment macOS-app-development iOS-app-development AI-model-integration
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 12 / 25

How are scores calculated?

Stars

1,492

Forks

44

Language

Rust

License

MIT

Last pushed

Mar 13, 2026

Commits (30d)

77

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/trymirai/uzu"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.