can-i-run-this-llm

Can I run this LLM?

Can a Intel Arc B580 (12GB) run Qwen3.5 9B?

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

Yes — it runs great.

Best fit: Qwen3.5 9B at Q6_K · 7.5 GB · 40–59 tok/s on a Intel Arc B580 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.1 GB65–98 tok/sRuns great
Q3_K_M4.7 GB59–88 tok/sRuns great
Q4_K_M5.7 GB50–75 tok/sRuns great
Q5_K_M6.6 GB44–66 tok/sRuns great
Q6_K7.5 GB40–59 tok/sRuns great
Q8_09.5 GB32–48 tok/sTight / slow
FP1617.9 GB18–27 tok/sWon't fit

Ran Qwen3.5 9B on a Intel Arc B580 (12GB)? Add your real numbers →