NVIDIA DGX™ Systems with Exeton

Datacenter

NVIDIA DGX H100

8x NVIDIA H100 GPUs, 32 PetaFLOPS, Dual Xeon Processors, and Robust Networking in One Powerhouse Server. Includes NVIDIA AI Software and 3-Year Warranty.

Equipped with 8x NVIDIA H100 Tensor Core GPUs SXM5
GPU memory totals 640GB
Achieves 32 petaFLOPS FP8 performance
Incorporates 4x NVIDIA® NVSwitch™ Link
System power usage peaks at ~10.2kW
Employs Dual 56-core 4th Gen Intel® Xeon® Scalable processors
Provides 2TB of system memory
Offers robust networking, including 4x OSFP ports, NVIDIA ConnectX-7 VPI, and options for 400 Gb/s InfiniBand or 200 Gb/s Ethernet
3 year manufacturer parts or replacement warranty included (return-to-base)

$350,000

Add to Cart Enquire Now Download PDF

High-Performance Server with NVIDIA H100 GPUs

The Gold Standard for AI Infrastructure

NVIDIA DGX H100 powers business innovation and optimization. The latest iteration of NVIDIA’s legendary DGX systems and the foundation of NVIDIA DGX SuperPOD™, DGX H100 is an AI powerhouse that features the groundbreaking NVIDIA H100 Tensor Core GPU. The system is designed to maximize AI throughput, providing enterprises with a highly refined, systemized, and scalable platform to help them achieve breakthroughs in natural language processing, recommender systems, data analytics, and much more. Available on-premises and through a wide variety of access and deployment options, DGX H100 delivers the performance needed for enterprises to solve the biggest challenges with AI.

The World’s Proven Choice for Enterprise AI

Drives Accelerated Performance

Maximize business innovation and optimization with NVIDIA DGX™ H100. As a vital component of the DGX platform and the newest iteration of NVIDIA's renowned DGX systems, DGX H100 serves as the cornerstone for NVIDIA DGX SuperPOD™, leveraging the revolutionary capabilities of the NVIDIA H100 Tensor Core GPU to drive accelerated performance.

DOWNLOAD DATASHEET

Explore DGX H100

Powering Accelerated Business Innovation

8 NVIDIA H100 GPUs, Providing 640 Gigabytes of Total GPU Memory
Each GPU Equipped with 18 NVIDIA® NVLink® Connections, Delivering 900 Gigabytes per Second of Bidirectional GPU-to-GPU Bandwidth
4 NVIDIA NVSwitches™, Delivering an Impressive 7.2 Terabytes per Second of Bidirectional GPU-to-GPU Bandwidth, a 1.5X Increase Compared to the Previous Generation
10 NVIDIA ConnectX®-7 Network Interfaces, Each Capable of 400 Gigabits-Per-Second, Providing a Peak Bidirectional Network Bandwidth of 1 Terabyte per Second
Dual Intel Xeon Platinum 8480C Processors, Boasting a Total of 112 Cores and Accompanied by 2 Terabytes of System Memory, Ensuring Exceptional Performance for Demanding AI Workloads

Break Through the Barriers to AI at Scale

Designed for the Most Demanding AI Workloads

As the world’s first system with the NVIDIA H100 Tensor Core GPU, NVIDIA DGX H100 breaks the limits of AI scale and performance. It features 9X more performance, 2X faster networking with NVIDIA ConnectX®-7 smart network interface cards (SmartNICs), and high-speed scalability for NVIDIA DGX SuperPOD. The next-generation architecture is supercharged for the largest, most complex AI jobs, such as natural language processing and deep learning recommendation models.

Unmatched AI Power and Scalability

NVIDIA Base Command powers every DGX system, enabling organizations to leverage the best of NVIDIA software innovation. Enterprises can unleash the full potential of their DGX investment with a proven platform that includes enterprise-grade orchestration and cluster management, libraries that accelerate compute, storage and network infrastructure, and an operating system optimized for AI workloads. Additionally, DGX systems include NVIDIA AI Enterprise, offering a suite of software optimized to streamline AI development and deployment.

Gallery

Your cart is empty

Add item to it now