1k desktop beats vendor sparse library 474× on Mistral-7B

Show HN: 1k desktop beats vendor sparse library 474× on Mistral-7B

1k desktop beats vendor sparse library 474× on Mistral-7B is a business in show hn launch.

Profile

I've been working on a sparse compute primitive for AI inference. The idea came on a bike ride — I'm a mathematician and serial entrepreneur, not a GPU engineer, and I wanted to see if the matrix math at the heart of every AI model could be restructured to skip unnecessary work while producing identical outputs. Results on my HP All-in-One (i7-1165G7, 4 cores, 64GB, Windows 11):Mistral-7B real weights, 0% sparsity (fully dense): 127× vs CPU dense, 474× vs CPU sparse, 0.7ms first token vs 49.4ms sparse, 99.2% less energy Llama-2-7B real weights, 0% sparsity: 59× vs dense, 228× vs sparse, 0.8ms first tokenOn NVIDIA B200 with real HuggingFace weights:Llama-4 Maverick 400B: 133.5× faster, 99.9%

1k desktop beats vendor sparse library 474× on Mistral-7B is positioned in show hn launch, a segment that rewards a clear, focused offering.

The company is listed at the Show HN launch stage of development.

Website: rolv.ai