Support dates
We do not have confirmed sales and support dates for this part number.
Send us the full DGX H100 order code, software release and support details before planning long-term use.
Ask us to check the current sales and support statusLoading products and specifications…

Build around your workload
NVIDIA DGX H100. AI Server. Ask for current pricing and help choosing the right configuration.
Tell us the configuration, quantity and destination. Your quotation will show availability, condition, warranty and delivery terms.
Start an order requestNVIDIA / PRODUCT DETAILS
See what is installed, then compare it with the platform limits. The maximum supported configuration may be different from what ships with this unit.
KEY SPECIFICATIONS / 01
Confirm drive carriers, backplane, controller and any required cables.
NVIDIA / ORDER & INSTALLATION DETAILS
Distinguish a GPU board, accelerator module and complete NVIDIA system.
Check the qualified host, original power arrangement and cooling.
Review the driver or compute stack and required interconnect components.
Technical overview
Use the full part number when comparing options or asking about system fit.
| GPU subsystem | 8 × NVIDIA H100 |
|---|---|
| GPU memory | 640 GB aggregate (8 × 80 GB) |
| Form factor | 8U rackmount |
| Cooling | Air cooling |
| Power reference | 10.2 kW maximum system power |
| Processor platform | 2 × Intel Xeon Platinum 8480C |
| System memory | 2 TB system memory |
| Local storage | 8 × 3.84 TB U.2 NVMe data cache; 2 × 1.92 TB M.2 boot |
| Network fabric | 8 × ConnectX-7, up to 400 Gb/s per card |
| Brand | NVIDIA |
| Model | DGX H100 |
| Catalog line | NVIDIA DGX |
| Manufacturer | NVIDIA |
| Model / P/N | NVIDIA DGX H100 |
| Category | AI Server |
| Product family | NVIDIA DGX |
| Product series | DGX AI Systems |
HOW THIS PRODUCT FITS YOUR SYSTEM
Choose how you plan to use this product.
Match the processor generation, socket population and required heatsink.
Check the installed modules, supported type and population rules.
Use this checklist to describe the change. The host system and full configuration determine which parts will fit.
YOUR QUOTE REQUEST
Add the quantity, options and installation details you want us to quote.
Confirm the exact manufacturer part number, host compatibility and included components. Optional software is quoted separately only when requested.
SUPPORT & REPLACEMENT
Check support dates, replacement options and whether continued use still makes sense.
We do not have confirmed sales and support dates for this part number.
Send us the full DGX H100 order code, software release and support details before planning long-term use.
Ask us to check the current sales and support statusProducts with similar names or connectors may still be incompatible. Compare the full specifications, installed system and software requirements.
Compare related products These products may be related, but we have not confirmed them as replacements.USING HARDWARE RESPONSIBLY
Consider repairability, remaining support and actual operating demand. Extending service life is useful only when the equipment still meets your security and reliability requirements.
Use measured average input power for the same workload. PSU ratings and processor TDP are different from total system power.
Energy difference = (current W − proposed W) × hours × units ÷ 1,000. Excludes cooling, embodied emissions and purchase costs.CONNECTION DETAILS
Choose the host adapters around the workload and the storage protocol. A server NIC, Fibre Channel HBA and SAS HBA serve different connections.
Browse the categories above for related equipment, then send us the full configuration so we can check the fit.
PRODUCT DETAILS
EXACT PLATFORM / SOURCE-REVIEWED SUMMARY
Aggregate GPU memory is the sum across installed GPUs, not one independently addressable memory pool. Actual configuration and supported options must be confirmed.
Plan DGX system quantities ↗See the product details and images below.
Platform overview
This page separates the server platform from the options that complete it. No processor, DIMM, drive, controller, adapter or service item is treated as interchangeable until its fit is checked against the model.
Chassis revision, regional SKU and current sales and support status are confirmed before parts are selected.
Processor family, socket count, thermal limits and memory population are checked together for the selected platform.
Drive media, form factor, backplane, controller or HBA, cabling and boot design are reviewed together.
NICs, accelerators, risers, power, firmware, rails, support and regional accessories are listed separately in the BOM.
Complete systems and spare parts are quoted separately. CPUs, DIMMs, drive carriers, controllers, NICs and PSUs are matched to the selected platform unless an approved compatible alternative is listed in the quotation.
Server configuration
Accelerator, adapter or DPU; exact board code and supported host.
Switch or computing system; its own SKU, firmware and configuration.
Product and edition; deployment rights and support where applicable.
Where NVIDIA lists both a current SKU and legacy Mellanox OPN, retain their exact documented mapping. A family name does not confirm a port layout, GPU board version or software entitlement.
Rack integration plan
Star Networking reviews upstream switching, storage path, OOB management, power input, rails and service details together so the delivered node can be installed without reworking the BOM.
25/100/400G uplinks, DAC/AOC, optics and OOB management are planned before shipment.
NVIDIA DGX H100 is staged with CPU, DIMM, storage, controller, NIC, PSU and firmware profile.
Boot media, hot data tier, capacity tier and backup path are separated in the BOM.
Service terms, serial numbers, labels, packing details and delivery milestones are recorded with the order.
Deployment / workload
Choose platform options and confirm the operating environment before finalizing the design.
Balance core density, memory capacity, boot resilience, east-west traffic and support policy.
Align memory, storage latency, controller mode and network throughput with the application profile.
Plan resilient boot, management access, power redundancy and a repeatable firmware baseline.
Standardize node BOMs, spares, firmware and delivery batches before multi-system rollout.
Compatibility and BOM checks
Model selection & order planning
NVIDIA DGX H100
Explore more products below. Please confirm compatibility before selecting a replacement.
Before you request a quote
Include the full model, manufacturer P/N, revision and quantity.
Tell us the host model, generation, installed configuration and required supporting hardware.
Specify condition, testing requirements, destination and requested delivery date.

AI Server
P/NDGX H200

AI Server
P/NDGX B300

AI Server
P/NDGX B200