Skip to main content
HardwareAI InfrastructurevSXM6

NVIDIA B100

by NVIDIA · paid · Last verified 2026-03-17

NVIDIA Blackwell architecture data center GPU. Successor to H100, delivering dramatically improved AI compute performance with next-generation NVLink interconnect and enhanced Transformer Engine with FP4 support.

https://www.nvidia.com/en-us/data-center/b100/
B
BAbove Average
Adoption: B+Quality: A+Freshness: A+Citations: B+Engagement: F

Specifications

License
Proprietary
Pricing
paid
Capabilities
ai-training, inference, fp4-compute, fp8-compute, nvlink5, transformer-engine
Integrations
cuda, tensorrt, nccl, cudnn
Use Cases
llm-training, inference-serving, hpc
API Available
No
Tags
gpu, data-center, training, inference, blackwell
Added
2026-03-17
Completeness
100%

Index Score

65.8
Adoption
70
Quality
99
Freshness
96
Citations
72
Engagement
0

Put AI to work for your business

Deploy this hardware alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.

Explore the full AI ecosystem on Agents as a Service