NVIDIA DGX H200 AI System (8x H200 Tensor Core GPU, 1.1TB HBM3e)

Brand: NVIDIA | Category: Servers

SKU: 935-24287-0070-000 | Part #: 935-24287-0070-000 | MPN: 935-24287-0070-000

Contact for Pricing — Request a Quote

Request a Quote Contact Us

About the NVIDIA DGX H200 AI System (8x H200 Tensor Core GPU, 1.1TB HBM3e)

The NVIDIA DGX H200 AI System (8x H200 Tensor Core GPU, 1.1TB HBM3e) from NVIDIA is enterprise-grade Servers hardware built for data centers. The NVIDIA DGX H200 is a purpose-built AI supercomputing system integrating eight NVIDIA H200 Tensor Core GPUs interconnected via fifth-generation NVLink, delivering a combined 1.1 TB of HBM3e memory with 3.35 TB/s of aggregate memory bandwidth. Built on the same Hopper GPU architecture as the H100, the H200 advances the platform with significantly higher memory capacity and bandwidth, enabling larger models to reside entirely in GPU memory and dramatically reducing data move Available in brand new condition. NVIDIA servers products are trusted by enterprises and data centers worldwide. Available from Omnixon Global. Contact our sales team to request a quote.

Technical Specifications

BrandNVIDIA
CategoryServers
SKU935-24287-0070-000
Part Number935-24287-0070-000
ConditionNew
Manufacturer Part Number935-24287-0070-000
GPU8x NVIDIA H200 Tensor Core GPU
GPU ArchitectureNVIDIA Hopper (GH100)
Total GPU Memory1.1 TB HBM3e
GPU Memory per GPU141 GB HBM3e
Aggregate GPU Memory Bandwidth3.35 TB/s
FP8 Tensor Core Performance (per GPU)3,958 TFLOPS (with Sparsity)
FP16 / BF16 Tensor Core Performance (per GPU)1,979 TFLOPS (with Sparsity)
FP64 Tensor Core Performance (per GPU)67 TFLOPS
GPU InterconnectNVLink 4.0, 900 GB/s bidirectional total bandwidth (all-to-all)
CPUDual Intel Xeon Platinum 8480C (Sapphire Rapids), 60 cores each
System Memory2 TB DDR5
Internal Storage8x 3.84 TB NVMe SSD (30.72 TB raw)
Network Adapters8x NVIDIA ConnectX-7 VPI (400GbE / NDR 400Gb/s InfiniBand)
Out-of-Band ManagementDedicated BMC with NVIDIA IPMI / Redfish support
Form Factor6U Rackmount
Power SupplyRedundant 10 kW (N+1)
Operating SystemDGX OS (Ubuntu-based, NVIDIA optimized)
Software StackNVIDIA Base Command, NGC Container Registry, CUDA 12.x, cuDNN, NCCL

Frequently Asked Questions about NVIDIA DGX H200 AI System (8x H200 Tensor Core GPU, 1.1TB HBM3e)

What does the NVIDIA DGX H200 AI System (8x H200 Tensor Core GPU, 1.1TB HBM3e) do?

The NVIDIA DGX H200 AI System (8x H200 Tensor Core GPU, 1.1TB HBM3e) is built for enterprise data-center workloads — virtualization (VMware, Proxmox, Nutanix), private cloud, database hosting, and AI/ML training. It fits standard EIA-310 server racks and supports redundant PSUs and hot-swap drives common in production environments.

What are the headline specs of the NVIDIA DGX H200 AI System (8x H200 Tensor Core GPU, 1.1TB HBM3e)?

Key specifications for the NVIDIA DGX H200 AI System (8x H200 Tensor Core GPU, 1.1TB HBM3e): new condition; manufacturer NVIDIA; manufacturer part number 935-24287-0070-000; gpu 8x NVIDIA H200 Tensor Core GPU; gpu architecture NVIDIA Hopper (GH100); total gpu memory 1.1 TB HBM3e; gpu memory per gpu 141 GB HBM3e. Manufacturer part number 935-24287-0070-000. For the full datasheet with electrical, environmental, and compliance details, contact our pre-sales engineering team.