Qwen on Intel Battlemage

Can I run Qwen3 30B-A3B on an Arc B580?

Not at Q4_K_M — it needs 18.8 GB against 10.5 GB available. You would need 2 of these cards.

Won't fit

18.8 GB of 10.5 GB · 180%
020 GB
Weights 17.3 GB
KV cache 0.8 GB
Runtime overhead 0.8 GB
Over the limit 8.3 GB

Short by 8.3 GB. You can run it with 24 of 48 layers on the Arc B580 and the rest in system RAM, at roughly 22.4 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation22.4tok/s
Prompt processing2892tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of Qwen3 30B-A3B on a Arc B580

Highlighted row is the highest quality that still fits at 8K context.

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 56.9 GB 58.4 GB Won't fit — 5.47
INT8 / W8A8 8.50 30.1 GB 31.6 GB Won't fit — 11.2
Q8_0 (GGUF) 8.50 30.1 GB 31.6 GB Won't fit — 11.2
FP8 (E4M3) 8.00 28.4 GB 30.0 GB Won't fit — 12.0
Q6_K 6.56 23.3 GB 24.9 GB Won't fit — 15.1
Q5_K_M 5.67 20.2 GB 21.7 GB Won't fit — 18.3
Q5_K_S 5.52 19.6 GB 21.2 GB Won't fit — 18.7
Q4_K_M 4.85 17.3 GB 18.8 GB Won't fit — 22.4
Q4_K_S 4.58 16.3 GB 17.9 GB Won't fit — 24.7
Q4_0 4.55 16.2 GB 17.8 GB Won't fit — 24.8
AWQ 4-bit 4.25 16.0 GB 17.5 GB Won't fit — 25.1
GPTQ 4-bit 4.25 16.0 GB 17.5 GB Won't fit — 25.1
MXFP4 4.25 16.0 GB 17.5 GB Won't fit — 25.1
IQ4_XS 4.25 15.2 GB 16.7 GB Won't fit — 27.6
Q3_K_M 3.91 14.0 GB 15.5 GB Won't fit — 31.1
IQ3_M 3.70 13.3 GB 14.8 GB Won't fit — 34.5
IQ3_XXS 3.06 11.1 GB 12.6 GB Won't fit — 48.6
Q2_K 2.63 9.6 GB 11.1 GB Won't fit 1K 70.1
IQ2_XXS 2.06 7.6 GB 9.1 GB Runs comfortably 23K 98.8
IQ1_M 1.75 6.5 GB 8.0 GB Runs comfortably 34K 105

Also worth checking

Qwen3 30B-A3B on every GPU
Full hardware tableEverything that runs on a Arc B580
Full model tableWhy the KV cache is the part that bites
Guide