B200 NVL (pair)
nvidia · blackwell · 360 GB HBM3e · 1800W TDP
VRAM
360 GB
BF16 TFLOPS
4500
Bandwidth
16000 GB/s
From
$10.50/hr
Spec Sheet
Pricing by Provider
| Provider | On-Demand | Reserved | Spot | Badge |
|---|---|---|---|---|
| coreweave | $14.00/hr | $10.50/hr | - | Cheapest |
| lambda | $11.49/hr | - | - |
Compatible Models (280)
Single GPU (257 models)
Multi-GPU (23 models)
Training Capabilities
Estimated GPU count for full fine-tuning (AdamW, BF16) and QLoRA
| Model Size | Full Fine-Tune | QLoRA |
|---|---|---|
| 7B model | 1 GPU | 1 GPU |
| 13B model | 1 GPU | 1 GPU |
| 70B model | 4 GPUs | 1 GPU |
Energy Efficiency
Estimated tokens/second per Watt for popular models
Similar GPUs
| GPU | VRAM | BF16 TFLOPS | BW (GB/s) | From |
|---|---|---|---|---|
| B300 | 288 GB | 2800 | 12000 | $0.00/hr |
| B100 SXM | 192 GB | 1750 | 8000 | $4.50/hr |
| GB200 NVL72 (per GPU) | 192 GB | 2250 | 8000 | $6.50/hr |
| GB300 NVL72 (per GPU) | 192 GB | 2500 | 8000 | $7.50/hr |
| B200 SXM | 180 GB | 2250 | 8000 | $4.49/hr |
Methodology Note
Performance estimates for the B200 NVL (pair)are based on InferenceBench's roofline performance model with CUDA kernel-level optimization including FlashAttention v2 and PagedAttention. Memory calculations account for model weights (360 GB HBM3e available), KV-cache allocation, and activation memory. Throughput predictions use the B200 NVL (pair)'s rated 16000 GB/s memory bandwidth and 4500 BF16 TFLOPS compute capacity as roofline ceilings, with empirical correction factors per GPU architecture (blackwell). See our full methodology.
Frequently Asked Questions
How many AI models can run on B200 NVL (pair)?
The B200 NVL (pair) can run 280 AI models from our database within a single node. Compatible models range across various parameter sizes depending on the quantization precision (BF16, FP8, INT4). Smaller models fit on a single GPU while larger models may require multi-GPU setups up to 4x B200 NVL (pair).
What is the B200 NVL (pair) inference throughput?
The B200 NVL (pair) delivers 4500 BF16 TFLOPS and 9000 FP8 TFLOPS with 16000 GB/s memory bandwidth. Actual inference throughput (tokens/sec) depends on the model size, precision, and batch size. Use our calculator for model-specific throughput estimates.
How much does B200 NVL (pair) cost per hour?
The B200 NVL (pair) is available starting from $10.50/hour via coreweave. Prices vary by provider and pricing tier (on-demand, reserved, spot). Compare pricing across all providers in the table above.