can-i-run-this-llm

Can I run this LLM?

Can a Intel Arc B580 (12GB) run GLM-4 9B?

GLM · MIT · estimated for a 12.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at Q6_K · 8.3 GB · 36–54 tok/s on a Intel Arc B580 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB66–99 tok/sRuns great
Q3_K_M5.0 GB56–83 tok/sRuns great
Q4_K_M6.2 GB46–70 tok/sRuns great
Q5_K_M7.1 GB41–62 tok/sRuns great
Q6_K8.3 GB36–54 tok/sRuns great
Q8_010.0 GB30–46 tok/sWon't fit
FP1618.8 GB17–25 tok/sWon't fit

Ran GLM-4 9B on a Intel Arc B580 (12GB)? Add your real numbers →