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
8,035
Last 7 days
+250
Last 30 days
+799
Last 12 months
+8,034
README badge
[](https://rustystars.dev/magnitudedev/magnitude)