MohammadHaishemKhawaja / hashyyView on GitHub
A full, unpruned 177B MoE model at 11.5 tok/s on one 12 GB GPU. Expert streaming for llama.cpp, with the measurement harness and every dead end.
β˜†22Oct 3, 2026Updated 2 weeks ago

Alternatives and similar repositories for hashyy

Users that are interested in hashyy 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?