NVIDIA DGX Vera Rubin NVL72 rack-scale system with 72 Rubin GPUs, 36 Vera CPUs, 20.7 TB HBM4, ConnectX-9, BlueField-4, and NVLink 6 for gigascale training and inference.

Ground, Overnight

Fast Shipping

In Stock

100k+ SKUs

Sales and Support

8/5 Support

New / Refurbished

Certified

NVIDIA DGX Vera Rubin NVL72 Rack-Scale AI System | DGX-RUBIN-NVL72

SKU: DGX-RUBIN-NVL72 Categories: , Brand:

⭐ Top Rated Verified Buyers
We are trusted for quality, reliability and fast shipping 💯
REQUEST A QUOTE
0 People watching this product now!
Description

NVIDIA DGX Vera Rubin NVL72 Rack-Scale AI System (DGX-RUBIN-NVL72)

NVIDIA DGX Vera Rubin NVL72 is NVIDIA’s integrated DGX implementation of the Vera Rubin NVL72 rack-scale architecture. It combines 72 Rubin GPUs, 36 Vera CPUs, NVLink 6 scale-up connectivity, ConnectX-9 SuperNICs, BlueField-4 DPUs, and NVIDIA DGX software and management for large AI factory deployments.

Availability / RFQ: Exact production configuration, allocation, partner fulfillment, deployment timeline, and site-readiness requirements should be verified during RFQ. Contact Catalyst Data Solutions to discuss current status, compatibility, configuration requirements, and sourcing options.
End-user / export compliance notice: Advanced AI accelerators and systems may be subject to applicable U.S. export controls, end-user/end-use restrictions, destination requirements, and OEM/channel policies. Catalyst may request purchaser, final end-user, intended-use, and deployment-location information before a quote or fulfillment can be approved. An RFQ does not guarantee allocation or shipment.

Technical Specifications

SKU DGX-RUBIN-NVL72
Product Type DGX Rack-Scale AI System
GPU / CPU Configuration 72x Rubin GPUs / 36x Vera CPUs
Total GPU Memory 20.7 TB HBM4
GPU Memory Bandwidth Up to 1,580 TB/s aggregate
Scale-Up 9x L1 NVIDIA NVLink Switch systems
Scale-Out Networking More than 144x ConnectX-9 VPI OSFP interfaces
Infrastructure DPUs 18x dual-port NVIDIA BlueField-4 VPI
Software NVIDIA Mission Control, NVIDIA AI Enterprise, NVIDIA DGX OS
Availability Status Contact for Current Availability

Deployment and Compatibility Considerations

  • Plan DGX Vera Rubin NVL72 as a complete data-center project, not as a conventional standalone server.
  • Validate scale-out fabric, optics, cable maps, storage throughput, management, power distribution, and cooling before installation.
  • Confirm facility liquid-cooling readiness, redundancy, CDU design, rack loading, and deployment services.
  • Coordinate DGX software, cluster management, security, support, and network design with the intended AI workload.

Common Use Cases

  • Gigascale AI training
  • Reasoning and agentic inference
  • Hyperscaler and neocloud AI factories
  • Sovereign AI infrastructure
  • Large multi-tenant AI services

Frequently Paired Infrastructure

  • Spectrum-X Ethernet or Quantum-X800 InfiniBand
  • ConnectX-9 SuperNICs and BlueField-4 DPUs
  • AI-native and high-throughput storage
  • 800G/1.6T optical and cable infrastructure
  • High-density rack power and liquid cooling

Official NVIDIA Documentation

NVIDIA DGX Vera Rubin NVL72 Datasheet

Frequently Asked Questions

What is the difference between DGX Vera Rubin NVL72 and the Vera Rubin NVL72 platform?

The platform defines the rack-scale architecture, while DGX Vera Rubin NVL72 is NVIDIA’s integrated DGX system implementation with NVIDIA software, management, support, and validated system-level design.

Are the DGX Vera Rubin NVL72 specifications final?

NVIDIA currently labels the published DGX specifications as preliminary, so project designs should confirm the current revision during procurement.

Additional information
product typeDGX Rack-Scale AI System
Platform / ArchitectureNVIDIA Vera Rubin NVL72
Accelerator Configuration72 Rubin GPUs / 36 Vera CPUs
NetworkingConnectX-9 + BlueField-4
Availability StatusContact for Current Availability
About brand
NVIDIA is the leader in GPU computing and AI infrastructure for high-performance workloads.

Recently Viewed Products