Hardware Datasheet · GPU Server
Nexus Compute
Nexus H200 128-GPU SuperPOD (16× HGX H200 Nodes)
A full-scale 128-GPU H200 pod for frontier training and large-scale HPC.
Overview
This 128-GPU H200 SuperPOD is a complete reference-architecture deployment — sixteen HGX H200 nodes, full NDR fat-tree fabric, and a certified parallel storage tier engineered to scale as one machine. Nexus Compute designs, sources through authorized channels, integrates, and acceptance-tests every layer, delivering a warranty-backed pod rather than a parts list.
Specifications
| GPU / Accelerator | 128× NVIDIA H200 141GB HBM3e SXM5 (16× HGX H200 nodes) |
| GPU Interconnect | NVSwitch intra-node; non-blocking NDR fat-tree inter-node |
| CPU | Dual Intel Xeon or AMD EPYC per node |
| Memory | Up to 2TB+ DDR5 ECC per node |
| Networking / Fabric | Quantum-2 NDR 400Gb/s InfiniBand, QM9700 spine/leaf |
| Storage | NVIDIA-certified parallel filesystem, GPUDirect Storage (multi-PB) |
| Management | NVIDIA Base Command + UFM fabric management |
| Form Factor | Multi-rack SuperPOD scalable unit |
| Warranty | Nexus-backed, NVIDIA AI Enterprise included |
Typical Use Cases
- ·Frontier and foundation model pretraining
- ·Large-scale distributed training across 16 nodes
- ·Converged HPC and AI scientific workloads
- ·Flagship sovereign or institutional AI 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.