can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA B200 (192GB) run GLM-4.7 Flash (MoE)?

GLM · MIT · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at FP16 · 59.9 GB · 262–393 tok/s on a NVIDIA B200 (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K9.7 GB337–506 tok/sRuns great
Q3_K_M12.9 GB331–497 tok/sRuns great
Q4_K_M18.2 GB322–483 tok/sRuns great
Q5_K_M21.3 GB316–474 tok/sRuns great
Q6_K24.7 GB311–466 tok/sRuns great
Q8_031.8 GB299–449 tok/sRuns great
FP1659.9 GB262–393 tok/sRuns great

Ran GLM-4.7 Flash (MoE) on a NVIDIA B200 (192GB)? Add your real numbers →