Hardware Datasheet · GPU Server
NVIDIA
NVIDIA DGX SuperPOD
A reference architecture for multi-node DGX clusters — fabric, storage and management designed together.
Overview
DGX SuperPOD is not a single product but NVIDIA’s reference architecture for building clusters out of DGX nodes: the InfiniBand fabric, the parallel storage, the management network and the rack layout, specified as one design rather than assembled from separate purchases. It exists because the commonest way a large AI build fails is buying the nodes first and discovering the fabric and storage afterwards.
Specifications
| Compute | DGX nodes — B200, H200 or H100 generation |
| Compute fabric | Rail-optimised InfiniBand |
| Storage | High-performance parallel storage, sized to the workload |
| Management | Separate out-of-band management network |
| Scale | Scale-unit based; node count specified with you |
| Delivery | Quoted as one bill of materials including fabric, storage and rack power |
Typical Use Cases
- ·Multi-node large language model training
- ·Enterprise AI platform build-outs
- ·Research computing centres
- ·Staged expansion of an existing DGX estate
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.