can-i-run-this-llm

Can I run this LLM?

Can a Intel Arc B580 (12GB) run Qwen3.5 4B?

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

Yes — it runs great.

Best fit: Qwen3.5 4B at Q8_0 · 4.5 GB · 57–85 tok/s on a Intel Arc B580 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M2.3 GB90–135 tok/sRuns great
Q4_K_M2.7 GB80–120 tok/sRuns great
Q5_K_M3.1 GB73–110 tok/sRuns great
Q6_K3.5 GB68–101 tok/sRuns great
Q8_04.5 GB57–85 tok/sRuns great
FP168.4 GB34–51 tok/sTight / slow

Ran Qwen3.5 4B on a Intel Arc B580 (12GB)? Add your real numbers →