can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H100 (80GB) run GLM-4.5 Air (MoE)?

GLM · MIT · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.5 Air (MoE) at Q3_K_M · 47.6 GB · 195–292 tok/s on a NVIDIA H100 (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K35.9 GB216–325 tok/sRuns great
Q3_K_M47.6 GB195–292 tok/sRuns great
Q4_K_M67.0 GB167–251 tok/sTight / slow
Q5_K_M78.7 GB154–231 tok/sWon't fit
Q6_K91.1 GB142–213 tok/sWon't fit
Q8_0117.4 GB122–183 tok/sWon't fit
FP16220.9 GB78–118 tok/sWon't fit

Ran GLM-4.5 Air (MoE) on a NVIDIA H100 (80GB)? Add your real numbers →