2140wtf on Nostr: Run GLM-5.2 — 744B Mixture-of-Experts — on hardware you already own. Pure C, zero ...

Run GLM-5.2 — 744B Mixture-of-Experts — on hardware you already own.
Pure C, zero dependencies, experts staged just-in-time across VRAM, RAM and disk.

"A 744B frontier-class MoE answering on a 25 GB machine — the proven floor —
up to 9+ tok/s on a workstation.
No cluster, no cloud bill, no API key."

quoting
nevent1q…yv4q

https://justvugg.github.io/colibri/