Categories / LLM Infrastructure
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, Intel, or just a CPU.
Created
Jun 2026
Total stars
7,922
Last 7 days
+124
Last 30 days
+701
Last 12 months
+7,911
README badge
[](https://rustystars.dev/magnitudedev/magnitude)