magnitudedev/
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.
by Magnitude Rust Apache-2.0 licence 568 forks Created Jun 2026 View on GitHub
- Stars
- 7,794
- 65% of magnitudedev's stars
- Rank
- #7,782
- of 851,984 repos, top 0.9%
- In Rust
- #362
- of 24,089 repos, top 2%
Among 851,984 repos
6.3k–10k stars: 4,211 repos, including magnitude
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #7,780
- Next milestone
- +30,378 stars to reach the top 0.1%
- Popular
- One of 66,569 repos with 1k+ stars