Local GPU Rigs for GLM 5.2 / 5.5 Unlimited Inference
Jul 4, 2026 · 633 messages · 63 active members
@jcartu argued a ~$150k EUR 8x 6000-card node (or ~$30k/mo B200 rental) runs FP8 GLM 5.2 at 120+ tps for 8 concurrent devs, with GLM 5.5 in August rumored at Opus 4.8 quality plus vision. Draft models (dflash) roughly do…
Read full digest →