magnitudedev/magnitude
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, or just a CPU.
7.1k
Stars
484
Forks
73.9
Radar Score
Rising
Momentum
Scoring Breakdown
Impact86.1
Velocity67.3
Health63.8
Growth Metrics
7-Day Stars
+463
30-Day Stars
+2.4k
Acceleration
0.75x
Language
Rust
Why it ranks
Strong momentum — adoption is accelerating week over week.