Can Arc B580 12GB run Qwen3-Next-80B-A3B-Instruct?

Intel · 12 GB GDDR6 · 456 GB/s bandwidth · Alibaba · 81.3B (active 3B) · MoE · model ctx up to 256K

No — Qwen3-Next-80B-A3B-Instruct at Q4 needs ≈ 46.02 GB even at 4K context, beyond the Arc B580 12GB's 12 GB GDDR6. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 18.5 tok/s (estimated, batch 1). FP16 needs ≈ 164.2 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	46.02 GB	No	18.8 est.
Q4	8K default	46.32 GB	No	18.5 est.
Q4	32K	48.12 GB	No	—
FP16	4K	163.9 GB	No	—
FP16	8K default	164.2 GB	No	—
FP16	32K	166.0 GB	No	—

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

Quant	Weights	KV cache	Overhead	Total needed	Arc B580 12GB VRAM
Q4	44.72 GB	0.6 GB	1 GB	46.32 GB	12 GB
FP16	162.6 GB	0.6 GB	1 GB	164.2 GB	12 GB

Other GPUs that run Qwen3-Next-80B-A3B-Instruct

• B200 192GB SXM — ≈1697.0 tok/s Q4 est.
• MI300X 192GB — ≈1124.2 tok/s Q4 est.
• H200 141GB SXM5 — ≈1018.2 tok/s Q4 est.
• H100 80GB SXM5 — ≈710.6 tok/s Q4 est.
• Gaudi 3 128GB — ≈694.9 tok/s Q4 est.
• A100 80GB SXM4 — ≈432.5 tok/s Q4 est.
• Mac Studio M3 Ultra 96GB — ≈173.7 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈169.7 tok/s Q4 est.

All GPUs for Qwen3-Next-80B-A3B-Instruct →

Other models for the Arc B580 12GB

• Qwen3-0.6B — ≈362.7 tok/s Q4 est.
• gemma-3-1b-it — ≈290.2 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈241.8 tok/s Q4 est.
• Qwen3-1.7B — ≈145.1 tok/s Q4 est.
• Phi-4-mini-instruct — ≈76.4 tok/s Q4 est.
• Phi-4-mini-reasoning — ≈76.4 tok/s Q4 est.
• gemma-3-4b-it — ≈74.4 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈72.5 tok/s Q4 est.

All models on the Arc B580 12GB →