nvidia HGX Rubin NVL8 board
NVIDIA HGX Rubin NVL8 8-GPU Baseboard | HGX-RUBIN-NVL8
Back to products
nvidia vera rubin nvl72 rack
NVIDIA DGX Vera Rubin NVL72 Rack-Scale AI System | DGX-RUBIN-NVL72
nvidia Vera Rubin NVL4
Click to enlarge

NVIDIA Vera Rubin NVL4 platform combining 4 Rubin GPUs and 2 Vera CPUs over NVLink-C2C for liquid-cooled MGX servers targeting HPC, AI.

Ground, Overnight

Fast Shipping

In Stock

100k+ SKUs

Sales and Support

8/5 Support

New / Refurbished

Certified

NVIDIA

NVIDIA Vera Rubin NVL4 HPC and AI Platform | RUBIN-NVL4

SKU: RUBIN-NVL4 Category: 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 Vera Rubin NVL4 HPC and AI Platform (RUBIN-NVL4)

NVIDIA Vera Rubin NVL4 is a compact high-performance computing and AI platform that combines four Rubin GPUs with two Vera CPUs. The GPUs are linked through a second-generation NVLink bridge using sixth-generation NVLink, while Vera CPUs connect through NVLink-C2C. NVIDIA positions NVL4 for scientific simulation and AI-for-science workloads in liquid-cooled MGX modular servers.

Availability/ RFQ: Exact system availability should be confirmed by manufacturer and region. 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 RUBIN-NVL4
Product Type HPC / AI Compute Platform
GPU Configuration 4x NVIDIA Rubin GPUs
CPU Configuration 2x NVIDIA Vera CPUs
GPU Interconnect Second-generation NVLink bridge using sixth-generation NVLink
CPU-GPU Interconnect NVIDIA NVLink-C2C
System Platform Liquid-cooled NVIDIA MGX modular servers
Primary Workload Focus Scientific computing and AI for science
Availability Status RFQ / Watchlist

Deployment and Compatibility Considerations

  • Select a validated liquid-cooled MGX or OEM system designed for the NVL4 platform.
  • Confirm facility cooling loop, rack power, CDU, manifolds, and serviceability before deployment.
  • Pair the system with a fabric sized for HPC collectives or distributed AI workloads.
  • Validate scientific software, CUDA-X libraries, MPI/communication stack, storage, and scheduler requirements.

Common Use Cases

  • Computational fluid dynamics and simulation
  • Climate, energy, and earth-science workloads
  • Computational chemistry and materials science
  • AI-for-science training and inference
  • HPC clusters that combine native scientific compute with AI

Frequently Paired Infrastructure

  • Liquid-cooled NVIDIA MGX systems
  • Spectrum-X Ethernet or Quantum-X800 InfiniBand
  • High-performance parallel storage
  • ConnectX networking
  • CDUs, rack power, and cooling distribution

Official NVIDIA Documentation

NVIDIA Vera Rubin NVL4

Frequently Asked Questions

How is Vera Rubin NVL4 different from NVL72?

NVL4 is a four-GPU, two-CPU platform aimed heavily at HPC and AI-for-science systems, while NVL72 is a full rack-scale 72-GPU AI platform for much larger training and inference deployments.

Does Vera Rubin NVL4 require liquid cooling?

NVIDIA positions the platform for compatible liquid-cooled MGX modular servers, so cooling infrastructure should be treated as part of the system design.

Additional information
product typeHPC / AI Compute Platform
Architecture / SeriesNVIDIA Vera Rubin NVL4
Accelerator Configuration4 Rubin GPUs / 2 Vera CPUs
Cooling TypeLiquid-Cooled MGX Platform
Availability StatusAnnounced / Upcoming
About brand
NVIDIA is the leader in GPU computing and AI infrastructure for high-performance workloads.

Recently Viewed Products