can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA A100 (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 · 57.2 GB · 136–203 tok/s on a NVIDIA A100 (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.3 GB153–230 tok/sRuns great
Q3_K_M57.2 GB136–203 tok/sRuns great
Q4_K_M73.0 GB117–176 tok/sWon't fit
Q5_K_M83.5 GB108–162 tok/sWon't fit
Q6_K99.0 GB96–144 tok/sWon't fit
Q8_0117.5 GB85–128 tok/sWon't fit
FP16221.0 GB52–78 tok/sWon't fit

Ran GLM-4.5 Air (MoE) on a NVIDIA A100 (80GB)? Add your real numbers →