Categories / LLM Infrastructure

Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.

Last push 5 hours ago

Created

Jun 2026

Total stars

8,067

Last 7 days

+269

Last 30 days

+816

Last 12 months

+8,068

README badge

Rusty Stars badge for magnitudedev/magnitude
[![Rusty Stars](https://rustystars.dev/badge/magnitudedev/magnitude.svg)](https://rustystars.dev/magnitudedev/magnitude)