DGX B200
DGX B200 is a NVIDIA AI system with 8 NVIDIA B200 and 2 Dual Intel Xeon.
Built from BenchGecko data as of April 14, 2026 · updates when the data changes
DGX B200 is a NVIDIA AI system with 8 NVIDIA B200 and 2 Dual Intel Xeon.
Basic
8-GPU Blackwell node for enterprises that don't need the full NVL72 rack. Air-cooled with NVLink 4.0 interconnect. The workhorse for inference at scale and moderate training workloads. Fits existing datacenter infrastructure without liquid cooling.
Deep
The dataset lists 80 PFLOPS of FP8 compute and 40 PFLOPS at BF16. It has 1.5 TB of HBM3e. Interconnect: NVLink 4.0. Power: 14 kW, air cooled.
Expert
Known deployments: Enterprise customers. Figures come from spec sheets and disclosures in the curated systems dataset, dated on the systems page.
Depending on why you're here
- ·8 × NVIDIA B200
- ·Interconnect: NVLink 4.0
- ·air cooling · 14 kW
- ·Compare systems on /systems/nvidia-dgx-b200
- ·Deployed by Enterprise customers
- ·DGX B200 is a big AI computer built from many NVIDIA B200 chips
Frequently Asked Questions
Read the primary sources
- NVIDIA DGX B200 datasheetwww.nvidia.com