Colibri: Running a 744B Parameter Model on 25GB of RAM
Discover Colibri: a tiny C engine that streams experts from disk to run massive 744B parameter models like GLM-5.2 on machines with only 25GB of RAM.
Tag glm-5.2
Discover Colibri: a tiny C engine that streams experts from disk to run massive 744B parameter models like GLM-5.2 on machines with only 25GB of RAM.