can-i-run-this-llm

Can I run this LLM?

Can a Intel Arc B580 (12GB) run Qwen3 14B?

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

Yes — it runs great.

Best fit: Qwen3 14B at Q3_K_M · 7.3 GB · 38–57 tok/s on a Intel Arc B580 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB46–69 tok/sRuns great
Q3_K_M7.3 GB38–57 tok/sRuns great
Q4_K_M9.0 GB32–48 tok/sTight / slow
Q5_K_M10.5 GB28–42 tok/sWon't fit
Q6_K12.1 GB25–37 tok/sWon't fit
Q8_015.7 GB19–29 tok/sWon't fit
FP1629.5 GB11–16 tok/sWon't fit

Ran Qwen3 14B on a Intel Arc B580 (12GB)? Add your real numbers →