NVIDIA DGX™ GB200 SYSTEMS

Powering the next AI revolution

NVIDIA DGX SuperPOD™ with NVIDIA DGX™ GB200 systems is purpose-built for training and inferencing trillion-parameter generative AI models.

Access the Technical Sheet Connect with Our Team

The best of AI in one place Enterprise Infrastructure for
Mission-Critical AI

NVIDIA DGX SuperPOD™ with NVIDIA DGX™ GB200 systems is purpose-built for training and inferencing trillion-parameter generative AI models.

Each liquid-cooled rack features 36 NVIDIA GB200 Grace Blackwell Superchips–36 NVIDIA Grace CPUs and 72 Blackwell GPUs–connected as one with NVIDIA NVLink. Multiple racks connect with NVIDIA Quantum InfiniBand to scale up to hundreds of thousands of GB200 Superchips.

Features *

Performance: 1440 petaFLOPS of FP4 AI performance
CPU Memory: 17 TB LPDDR5X
GPU Memory HBM3e: 13.4 TB
NVLink Bandwidth: 130TB/s

* Please note that those data are specific to one rack

PNY ADDED VALUE SERVICES

Presales
Support

Our team of experts collaborates with clients to understand their unique needs, guiding them toward the optimal solutions for their specific challenges.

Proof Of Concept
Support

We also provide POC Support, ensuring our clients can try before they buy with testing, benchmarks and evaluation.

Logistics
& Operations

To drive you "To Success", we provide Strong Logistic and Operation Abilities, guaranteeing seamless deployment.

Installation Service
& Support

To keep it all running smoothly, we provide Installation Services Support, ensuring that our solutions are properly installed and configured for optimal performance.

INNOVATION, RELIABILITY, AND EXPERTISE FOR SEAMLESS INFRASTRUCTURE MANAGEMENT ENTERPRISE GENERATIVE AI INFRASTRUCTURE WITH CONSTANT UPTIME

Enterprise-Class Generative AI Infrastructure

This next generation of NVIDIA DGX SuperPOD™ is purpose-built to deliver extreme performance and consistent uptime for superscale generative AI training and inference workloads

Maximize Developer Productivity With Constant Uptime

NVIDIA DGX SuperPOD™ with NVIDIA DGX™ GB200 systems delivers constant uptime with full-stack resilience for AI infrastructure.

Supercomputing for Generative AI

To achieve training and latency-sensitive inference on state-of-the-art trillion-parameter models, NVIDIA DGX SuperPOD™ with NVIDIA DGX™ GB200 systems can scale up to tens of thousands of NVIDIA Grace Blackwell Superchips.

GET IN TOUCH

Follow PNY Pro

Sign Up Now

Transform your data center operations! Join our newsletter to receive exclusive podcasts, virtual events, and expert information on data center and networking innovations.