Skip to content
crgregersen / m10disView on GitHub
Qwen3.8-Flash-Next-FP8 (48-layer MoE, 512 experts) on one RTX 3070 Ti plus 24 Maxwell GPUs from six Tesla M10 cards. PCIe multicast, GPU page-table remapping, 96 tok/s decode.
☆37Nov 7, 2026Updated this week

Alternatives and similar repositories for m10dis

Users that are interested in m10dis 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?