B100 SXM
nvidia · blackwell · 192 GB HBM3e · 700W TDP
VRAM
192 GB
BF16 TFLOPS
1750
Bandwidth
8000 GB/s
From
$4.50/hr
Spec Sheet
Pricing by Provider
| Provider | On-Demand | Reserved | Spot | Badge |
|---|---|---|---|---|
| coreweave | $6.00/hr | $4.50/hr | - | Cheapest |
| lambda | $4.99/hr | - | - |
Compatible Models (280)
Single GPU (248 models)
Multi-GPU (32 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 | 2 GPUs | 1 GPU |
| 70B model | 7 GPUs | 1 GPU |
Energy Efficiency
Estimated tokens/second per Watt for popular models
Similar GPUs
| GPU | VRAM | BF16 TFLOPS | BW (GB/s) | From |
|---|---|---|---|---|
| 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 |
| B300 | 288 GB | 2800 | 12000 | $0.00/hr |
| RTX 5090 | 32 GB | 210 | 1792 | $0.89/hr |
Methodology Note
Performance estimates for the B100 SXMare based on InferenceBench's roofline performance model with CUDA kernel-level optimization including FlashAttention v2 and PagedAttention. Memory calculations account for model weights (192 GB HBM3e available), KV-cache allocation, and activation memory. Throughput predictions use the B100 SXM's rated 8000 GB/s memory bandwidth and 1750 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 B100 SXM?
The B100 SXM 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 8x B100 SXM.
What is the B100 SXM inference throughput?
The B100 SXM delivers 1750 BF16 TFLOPS and 3500 FP8 TFLOPS with 8000 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 B100 SXM cost per hour?
The B100 SXM is available starting from $4.50/hour via coreweave. Prices vary by provider and pricing tier (on-demand, reserved, spot). Compare pricing across all providers in the table above.