EricLBuehler/mistral.rs

Fast, flexible LLM inference

65
/ 100
Established

Mistral.rs helps you efficiently run large language models (LLMs) on your own computer or server. You input a model, text prompts, and optional images or audio, and it outputs generated text, descriptions, or even new images. This tool is for developers, researchers, and engineers who need to deploy and interact with powerful AI models directly within their applications.

6,681 stars. Actively maintained with 32 commits in the last 30 days.

Use this if you need to integrate diverse multimodal AI capabilities (text, image, audio, video) into your applications with high performance and full control over model quantization.

Not ideal if you're looking for a simple, no-code AI chat interface or don't have programming experience to integrate an SDK or use a CLI.

LLM deployment AI inference multimodal AI machine learning engineering AI application development
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

6,681

Forks

540

Language

Rust

License

MIT

Last pushed

Feb 27, 2026

Commits (30d)

32

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/EricLBuehler/mistral.rs"

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