Hardware Datasheet · GPU Server
NVIDIA
NVIDIA DGX B200
Eight Blackwell GPUs and 1,440GB of HBM3e in NVIDIA’s unified training and inference platform.
Overview
DGX B200 is NVIDIA’s Blackwell-generation enterprise AI system, pairing eight B200 GPUs on an NVLink baseboard with 1,440GB of HBM3e and a fifth-generation NVSwitch fabric. It is bought as a complete, supported platform rather than assembled: NVIDIA specifies the chassis, the networking and the software environment together, which is the point for teams that want one accountable vendor across the stack. We source, configure and deliver it with the fabric and storage specified alongside.
Specifications
| GPU / Accelerator | 8× NVIDIA Blackwell B200 |
| GPU Memory | 1,440GB HBM3e total |
| GPU Interconnect | 5th-generation NVLink with NVSwitch |
| CPU | Dual Intel Xeon Platinum |
| System Memory | Up to 4TB DDR5 (configuration confirmed at quote) |
| Networking | OSFP ports for 400Gb/s InfiniBand or Ethernet; BlueField-3 DPUs |
| Form Factor | 10U rackmount, air-cooled |
| Sourcing | Configured and supplied by Nexus Compute; availability confirmed with quote |
Typical Use Cases
- ·Large language model training and fine-tuning
- ·High-throughput production inference
- ·Multi-node clusters built to the SuperPOD reference architecture
- ·Consolidating mixed AI workloads onto one supported platform
Industries
Warranty & Support
Supplied through authorized channels with full manufacturer warranty. On-site, next-business-day support options available. Every system is configured, tested, and documented before delivery, with asset and warranty records provided for enterprise audit requirements.
Request a tailored quote
Configurations are tailored per engagement — contact us for pricing and lead times.
sales@nexus-compute.com
+1 737 276 1016
nexus-compute.com
Specifications are indicative and configured to each engagement. All product names, logos, and trademarks are the property of their respective owners. Nexus Compute is an independent enterprise hardware supplier.