johnfink8 / sfnxView on GitHub
CUDA engine that splits every layer of a production quality MoE LLM across three PCIe V100 cards delivering 382 tok/s on a used $1,800 box.
☆43Oct 31, 2026Updated this week

Alternatives and similar repositories for sfnx

Users that are interested in sfnx are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?