NVIDIA Nemotron 3 Nano
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Parameters
31.6B
Context
1024K
Downloads
859.2K
Likes
810
Architecture
moe_transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 79.4 GB RAM 119.1 · Disk 130.8 | 98.5 GB RAM 147.8 · Disk 156.8 | 198.8 GB RAM 298.2 · Disk 195.8 |
| FP88bit | 42.2 GB RAM 63.3 · Disk 84.9 | 59.6 GB RAM 89.4 · Disk 110.9 | 158.2 GB RAM 237.3 · Disk 149.9 |
| INT88bit | 42.2 GB RAM 63.3 · Disk 84.9 | 59.6 GB RAM 89.4 · Disk 110.9 | 158.2 GB RAM 237.3 · Disk 149.9 |
| AWQ4bit | 24.3 GB RAM 36.4 · Disk 62.8 | 40.9 GB RAM 61.3 · Disk 88.8 | 138.7 GB RAM 208.0 · Disk 127.8 |
| GPTQ4bit | 24.5 GB RAM 36.7 · Disk 63.1 | 41.1 GB RAM 61.7 · Disk 89.1 | 138.9 GB RAM 208.4 · Disk 128.1 |
| GGUF4bit | 25.0 GB RAM 37.4 · Disk 63.7 | 41.6 GB RAM 62.4 · Disk 89.7 | 139.4 GB RAM 209.1 · Disk 128.7 |
GPU Recommendations
1× H100 SXM
80 GB VRAM
≈ 219.4 tok/s
Effective production throughput ≈ 153.6 tok/s
score 0.6259
4× Tesla V100
64 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5687
8× H200 SXM
1128 GB VRAM
≈ 1005.9 tok/s
Effective production throughput ≈ 704.1 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 50.3 tok/s
Effective production throughput ≈ 35.2 tok/s
score 0.6639
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX A6000
48 GB VRAM
$210
/mo · vast
L40S
48 GB VRAM
$341
/mo · vast
RTX PRO 6000 WS
48 GB VRAM
$482
/mo · vast
RTX PRO 6000 S
48 GB VRAM
$633
/mo · vast
A100 80GB
80 GB VRAM
$876
/mo · vast