can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA DGX Spark (GB10, 128GB) run GLM-4.5 Air (MoE)?

GLM · MIT · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.5 Air (MoE) at Q4_K_M · 73.0 GB · 19–28 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.3 GB27–41 tok/sRuns great
Q3_K_M57.2 GB23–34 tok/sRuns great
Q4_K_M73.0 GB19–28 tok/sRuns great
Q5_K_M83.5 GB17–25 tok/sTight / slow
Q6_K99.0 GB15–22 tok/sWon't fit
Q8_0117.5 GB13–19 tok/sWon't fit
FP16221.0 GB7–11 tok/sWon't fit

Ran GLM-4.5 Air (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →