Magnitude
Run open models as fast as your hardware allows
About
Magnitude is an open source inference engine that optimizes each model for your exact hardware. When you download a model, Magnitude spends up to a minute tuning its kernels to find the fastest configuration for your hardware. On the same hardware, it's 2x faster than Ollama. It works on Apple Silicon, NVIDIA, AMD, or just a CPU. One click connects it to the agent you already use (Pi, OpenCode, Hermes, Codex, and more).
Topics
- Location
- San Francisco, CA, United States
- Team size
- 2 employees
- YC batch
- Summer 2025
- Status
- Active
- Stage
- Early stage
