can-i-run-this-llm

Can I run this LLM?

Can a Intel Arc B580 (12GB) run Gemma 3 12B?

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

Yes — it runs great.

Best fit: Gemma 3 12B at Q4_K_M · 7.3 GB · 34–51 tok/s on a Intel Arc B580 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.8 GB46–69 tok/sRuns great
Q3_K_M6.0 GB39–59 tok/sRuns great
Q4_K_M7.3 GB34–51 tok/sRuns great
Q5_K_M8.5 GB31–46 tok/sWon't fit
Q6_K9.7 GB28–41 tok/sWon't fit
Q8_012.5 GB22–34 tok/sWon't fit
FP1623.5 GB13–19 tok/sWon't fit

Ran Gemma 3 12B on a Intel Arc B580 (12GB)? Add your real numbers →