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 · 99.0 GB · 167–251 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.3 GB231–346 tok/sRuns great
Q3_K_M57.2 GB213–319 tok/sRuns great
Q4_K_M73.0 GB193–289 tok/sRuns great
Q5_K_M83.5 GB182–272 tok/sRuns great
Q6_K99.0 GB167–251 tok/sRuns great
Q8_0117.5 GB153–229 tok/sTight / slow
FP16221.0 GB103–154 tok/sWon't fit

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