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. 🐦

github.com/justvugg/colibriUpdated 3mo ago
Loading community details…

Community

Create post
Ask or share about colibri…
Loading...
colibri on Pinokio