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.

194 best points · 180 comments · 3 Hacker News posts · 7,729 GitHub stars · View on GitHub

Hacker News discussions

• Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agents (194 points, 96 comments, by anerli, 2026-09-30)
• Show HN: Magnitude – open-source, AI-native test framework for web apps (179 points, 44 comments, by anerli, 2025-04-25)
• Show HN: Magnitude – Open-source AI browser automation framework (145 points, 40 comments, by anerli, 2025-06-26)