can-i-run-this-llm

Can I run this LLM?

Can a Intel Arc B580 (12GB) run Qwen3 8B?

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

Yes — it runs great.

Best fit: Qwen3 8B at Q6_K · 6.7 GB · 41–61 tok/s on a Intel Arc B580 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.3 GB70–105 tok/sRuns great
Q3_K_M4.1 GB60–90 tok/sRuns great
Q4_K_M5.0 GB51–77 tok/sRuns great
Q5_K_M5.9 GB46–69 tok/sRuns great
Q6_K6.7 GB41–61 tok/sRuns great
Q8_08.7 GB33–49 tok/sTight / slow
FP1616.4 GB19–28 tok/sWon't fit

Ran Qwen3 8B on a Intel Arc B580 (12GB)? Add your real numbers →