← AI Hashrate

Can Arc B580 12GB run NVIDIA-Nemotron-3-Nano-4B-BF16?

Intel · 12 GB GDDR6 · 456 GB/s bandwidth · NVIDIA · 4.0B · model ctx up to 256K

Yes — the Arc B580 12GB (12 GB GDDR6) can run NVIDIA-Nemotron-3-Nano-4B-BF16. At Q4 with the default 8K context it needs ≈ 4.0 GB VRAM (weights 2.2 GB + KV cache 0.8 GB + 1 GB runtime overhead), which fits within 12 GB. Decode at Q4/8K: ≈ 72.5 tok/s (estimated, batch 1). FP16 (≈ 9.8 GB) also fits, at ≈ 19.9 tok/s (estimated). 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

QuantContextVRAM neededFits?tok/s (decode)
Q44K3.6 GBYes72.5 est.
Q48K default4.0 GBYes72.5 est.
Q432K6.4 GBYes72.5 est.
FP164K9.4 GBYes19.9 est.
FP168K default9.8 GBYes19.9 est.
FP1632K12.2 GBNo55.1 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

QuantWeightsKV cacheOverheadTotal neededArc B580 12GB VRAM
Q42.2 GB0.8 GB1 GB4.0 GB12 GB
FP168.0 GB0.8 GB1 GB9.8 GB12 GB

Other GPUs that run NVIDIA-Nemotron-3-Nano-4B-BF16

All GPUs for NVIDIA-Nemotron-3-Nano-4B-BF16 →

Other models for the Arc B580 12GB

All models on the Arc B580 12GB →