JustVugg

@justvugg · GitHub · 1 works

Builds a tiny C engine that runs massive 744B MoE language models on consumer hardware by streaming experts fr

github.com/justvugg

Recent posts by JustVugg

• JustVugg/colibri - Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦 · Repo, Jul 2026 · github.com

Topics JustVugg posts about

• GLM on Instagram - 1 post · Best GLM creators