can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5060 Laptop (8GB) run GLM-4 9B?

GLM · MIT · estimated for a 8.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at Q3_K_M · 5.0 GB · 48–72 tok/s on a NVIDIA RTX 5060 Laptop (8GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB57–86 tok/sRuns great
Q3_K_M5.0 GB48–72 tok/sRuns great
Q4_K_M6.2 GB40–60 tok/sTight / slow
Q5_K_M7.1 GB35–53 tok/sWon't fit
Q6_K8.3 GB31–46 tok/sWon't fit
Q8_010.0 GB26–39 tok/sWon't fit
FP1618.8 GB14–22 tok/sWon't fit

Ran GLM-4 9B on a NVIDIA RTX 5060 Laptop (8GB)? Add your real numbers →