Magnitude Open-Source Engine Hits Hacker News Top With Up to 2x llama.cpp Speed
Magnitude, an open-source local inference engine from YC S25, auto-compiles and tunes kernels for the user's hardware, delivering up to 2x faster decoding than llama.cpp (about 92% gains on Metal) and topped Hacker News.
2026-10-01 ~ 2026-10-01 · 3 related posts
- Magnitude (YC S25) Open-Sources Inference Engine with Up to 2x Faster Decode Than llama.cpp — petrusenko_max · 2026-10-01
- Magnitude inference engine hits #1 on HN, claims up to 2x faster local open-model runs than llama.cpp — nickbaumann_ · 2026-10-01
- Magnitude: open-source inference engine that self-tunes kernels, up to 2x faster than llama.cpp — paranoidray · 2026-10-01