Show HN: Colibri Runs GLM-5.2's 744B MoE on a 25GB-RAM Consumer Machine in Pure C

Hacker News / JustVugg (GitHub)·high signal

Topping HN at 767 points and 189 comments, Colibri exploits the structure of a 744B mixture-of-experts model: only ~40B params activate per token and only ~11GB of those change between tokens. The dense part (attention, shared experts, embeddings, ~17B params at int4, ~9.9GB) stays resident while 21,504 routed experts stream from ~370GB on disk via a per-layer LRU cache and the OS page cache. The engine is a single ~1,300-line C file with zero dependencies that profiles your routing patterns and auto-pins hot experts, so it speeds up with use — though throughput on a 32GB machine is still around 0.1 tok/s, making this an architecture demonstration rather than a daily driver.