NVIDIA® B200
The NVIDIA B200 is NVIDIA's flagship data center GPU based on the Blackwell architecture, delivering unprecedented AI training and inference performance.
Availability
Available on Rackrr through our marketplace providers. Check the platform for real-time pricing and availability.
Specifications
| Component | Details |
|---|---|
| GPU Model | NVIDIA® B200 |
| Architecture | NVIDIA Blackwell |
| CUDA Cores | 18,432 |
| Tensor Cores | 576 (5th Gen) |
| VRAM | 192 GB |
| VRAM Type | HBM3e |
| Memory Bandwidth | 8 TB/s |
| TDP (Thermal Design Power) | 1000W |
| Form Factor | SXM |
| Interconnect | NVLink 5th Gen (1.8 TB/s) |
| FP8 Performance | 9 PFLOPS |
| FP16 Performance | 4.5 PFLOPS |
| Deep Learning Frameworks | PyTorch, TensorFlow, JAX |
Use Cases
- Large-scale AI model training
- Generative AI inference at scale
- High-performance computing (HPC)
- Large language model (LLM) fine-tuning