can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run GLM-4.7 Flash (MoE)?

GLM · MIT · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at FP16 · 59.9 GB · 220–330 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K9.7 GB320–480 tok/sRuns great
Q3_K_M12.9 GB311–467 tok/sRuns great
Q4_K_M18.2 GB297–446 tok/sRuns great
Q5_K_M21.3 GB290–434 tok/sRuns great
Q6_K24.7 GB282–423 tok/sRuns great
Q8_031.8 GB267–400 tok/sRuns great
FP1659.9 GB220–330 tok/sRuns great

Ran GLM-4.7 Flash (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →