Skip to main content

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

ComponentDetails
GPU ModelNVIDIA® B200
ArchitectureNVIDIA Blackwell
CUDA Cores18,432
Tensor Cores576 (5th Gen)
VRAM192 GB
VRAM TypeHBM3e
Memory Bandwidth8 TB/s
TDP (Thermal Design Power)1000W
Form FactorSXM
InterconnectNVLink 5th Gen (1.8 TB/s)
FP8 Performance9 PFLOPS
FP16 Performance4.5 PFLOPS
Deep Learning FrameworksPyTorch, TensorFlow, JAX

Use Cases

  • Large-scale AI model training
  • Generative AI inference at scale
  • High-performance computing (HPC)
  • Large language model (LLM) fine-tuning