ai-setup
Colibri – Run GLM-5.2 on Your Machine (Pure C, 25 GB RAM)
Colibri is a pure-C MoE runtime that streams 744B-parameter GLM-5.2 from disk to consumer hardware. Zero Python, zero GPU required — ~25 GB RAM and you are running a frontier model locally.
#ai-setup#local-llm#open-source