Can Arc B570 10GB run NVIDIA-Nemotron-3-Nano-4B-BF16?
Intel · 10 GB GDDR6 · 380 GB/s bandwidth ·
NVIDIA · 4.0B · model ctx up to 256K
Yes — the Arc B570 10GB (10 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 10 GB. Decode at Q4/8K: ≈ 60.5 tok/s (estimated, batch 1). FP16 needs ≈ 9.8 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
3.6 GB
Yes
60.5est.
Q4
8K default
4.0 GB
Yes
60.5est.
Q4
32K
6.4 GB
Yes
60.5est.
FP16
4K
9.4 GB
Yes
16.6est.
FP16
8K default
9.8 GB
No
49.5est.
FP16
32K
12.2 GB
No
31.9est.
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 B570 10GB VRAM
Q4
2.2 GB
0.8 GB
1 GB
4.0 GB
10 GB
FP16
8.0 GB
0.8 GB
1 GB
9.8 GB
10 GB
Other GPUs that run NVIDIA-Nemotron-3-Nano-4B-BF16