trymirai/uzu
A high-performance inference engine for AI models
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.
Stars
1,492
Forks
44
Language
Rust
License
MIT
Category
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.
Related tools
justrach/bhumi
⚡ Bhumi – The fastest AI inference client for Python, built with Rust for unmatched speed,...
lipish/llm-connector
LLM Connector - A unified interface for connecting to various Large Language Model providers
keyvank/femtoGPT
Pure Rust implementation of a minimal Generative Pretrained Transformer
ShelbyJenkins/llm_client
The Easiest Rust Interface for Local LLMs and an Interface for Deterministic Signals from...
rustformers/llm
[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models