Home/LLM Frameworks/mistral.rs
mistral.rs logo

mistral.rs

Enrichment pending
EricLBuehler/mistral.rs

Fast, flexible LLM inference

GraphCanon updated today · GitHub synced today

7.5k
Stars
655
Forks
374
Open issues
44
Watchers
4d
Last push
Rust MITCreated Feb 26, 2024

Trust & integrity

Full report
Maintenance
Very active (3d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Personal account
As of today · Source: github_public_v1
Security (OSV)
No lockfile
As of today · Source: none

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

Fast, flexible LLM inference

Capability facts

Deploy
Self-host

Source: dockerfile:Dockerfile · Jul 11, 2026

Docker
Dockerfile present

Source: dockerfile:Dockerfile · Jul 11, 2026

Languages
rust

Source: github.language · Jul 11, 2026

Categories

Tags

README

Install

Linux/macOS:

curl --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/EricLBuehler/mistral.rs/master/install.sh | sh

Windows (PowerShell):

irm https://raw.githubusercontent.com/EricLBuehler/mistral.rs/master/install.ps1 | iex

Downloads a self-contained prebuilt binary for your platform (Metal on Apple Silicon; per-GPU CUDA or CPU on Linux; CPU on Windows), falling back to a source build if none matches. No Rust or CUDA toolkit needed for the prebuilt path.

Manual installation, accelerator details & other platforms


Recommend settings for your hardware and emit a config file

mistralrs tune -m Qwen/Qwen3-4B --emit-config config.toml


Docker

Prebuilt CPU and CUDA images are published to GHCR. Pull commands, tags, and Kubernetes notes are in the Docker guide.