Can Arc B580 12GB run Phi-4?

Intel · 12 GB GDDR6 · 456 GB/s bandwidth · Microsoft · 14.7B · model ctx up to 16K

Partly — Phi-4 at Q4 fits the Arc B580 12GB (12 GB GDDR6) at 4K context (≈ 10.56 GB) but not at the default 8K (≈ 12.03 GB needed). Use a shorter context or partial offload. Decode at Q4/8K: ≈ 56.1 tok/s (estimated, batch 1). FP16 needs ≈ 33.34 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	10.56 GB	Yes	19.7 est.
Q4	8K default	12.03 GB	No	56.1 est.
Q4	32K	20.84 GB	No	18.7 est.
FP16	4K	31.87 GB	No	2.2 est.
FP16	8K default	33.34 GB	No	2.0 est.
FP16	32K	42.16 GB	No	1.3 est.

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	8.09 GB	2.94 GB	1 GB	12.03 GB	12 GB
FP16	29.4 GB	2.94 GB	1 GB	33.34 GB	12 GB

Other GPUs that run Phi-4

• B200 192GB SXM — ≈346.3 tok/s Q4 est.
• MI300X 192GB — ≈229.4 tok/s Q4 est.
• H200 141GB SXM5 — ≈207.8 tok/s Q4 est.
• H100 80GB SXM5 — ≈145.0 tok/s Q4 est.
• Gaudi 3 128GB — ≈141.8 tok/s Q4 est.
• A100 80GB SXM4 — ≈88.3 tok/s Q4 est.
• RTX 5090 32GB — ≈77.6 tok/s Q4 est.
• RTX 4090 24GB — ≈43.6 tok/s Q4 est.

All GPUs for Phi-4 →

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 →