can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run GLM-4.5 Air (MoE)?

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

Yes — it runs great.

Best fit: GLM-4.5 Air (MoE) at Q6_K · 91.1 GB · 174–261 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K35.9 GB247–371 tok/sRuns great
Q3_K_M47.6 GB227–340 tok/sRuns great
Q4_K_M67.0 GB200–300 tok/sRuns great
Q5_K_M78.7 GB187–280 tok/sRuns great
Q6_K91.1 GB174–261 tok/sRuns great
Q8_0117.4 GB153–229 tok/sTight / slow
FP16220.9 GB103–154 tok/sWon't fit

Ran GLM-4.5 Air (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →