can-i-run-this-llm

Can I run this LLM?

Can a Intel Arc B580 (12GB) run Gemma 4 12B?

Gemma · Apache 2.0 · estimated for a 12.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 12B at Q5_K_M · 8.4 GB · 35–52 tok/s on a Intel Arc B580 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M5.7 GB48–72 tok/sRuns great
Q4_K_M7.1 GB40–60 tok/sRuns great
Q5_K_M8.4 GB35–52 tok/sRuns great
Q6_K9.8 GB30–45 tok/sWon't fit
Q8_012.7 GB24–36 tok/sWon't fit
FP1623.8 GB13–20 tok/sWon't fit

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