Helldez /BigMoeOnEdge

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.

★ 991⑂ 102
C++Created 2026-07-10
991
stars
102
forks
–
watchers
–
prs
–
issues
–
releases

Snapshot: 2026-11-17T10:29:19Z · Data license Apache-2.0 · JSON