Skip to content
Back to product
N
NexusCompute

Hardware Datasheet · GPU Server

Nexus Compute

Nexus Compute

Nexus Compute GB200 NVL72 SuperPOD-Ready Scale Unit

Multi-rack Grace-Blackwell AI factory wired for non-blocking scale-out.

Overview

This SuperPOD-ready scale unit interconnects multiple GB200 NVL72 racks over a non-blocking Quantum-X800 InfiniBand fabric to form an AI factory engineered for the largest training runs. Nexus Compute designs, sources, integrates, and warranty-backs the multi-rack system through authorized channels, coordinating compute, liquid cooling, fabric, and storage so it commissions as one accountable build.

Specifications

ComputeMultiple GB200 NVL72 racks (72 Blackwell GPUs each)
Intra-Rack Link5th-gen NVLink Switch, 130TB/s per rack
Cluster FabricNon-blocking Quantum-X800 InfiniBand with SHARP
Shared StorageHigh-throughput parallel filesystem
OrchestrationSlurm or Kubernetes + GPU/fabric monitoring
CoolingLiquid-cooled, multi-rack
ScaleFrom one rack to multi-rack SuperPOD (configurable)
DeploymentDesign, sourcing, integration, and commissioning

Typical Use Cases

  • ·Fleet-scale foundation model training
  • ·AI-factory and SuperPOD build-outs
  • ·Sovereign and national-scale AI compute
  • ·Multi-rack research and HPC clusters

Industries

AI & Machine LearningGovernment & DefenseHPCTelecomHigher Education & Research

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.