a6deef8e4448dd778ac3a37917b70a161ee29940
Description
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Languages
C
49.8%
Python
26.4%
HTML
7.5%
Cuda
6.3%
TypeScript
4.2%
Other
5.7%