Procurement profile
Where this model makes sense
For companies that need full-stack AI infrastructure rather than a self-built server.
- AI center of excellence;
- enterprise training and inference;
- DGX BasePOD and SuperPOD architectures.
DGX Platform / Enterprise AI
NVIDIA DGX H100 / H200
DGX H100/H200 is a complete AI platform. Before quoting we verify not only the system, but also room, racks, power, cooling, networking and service readiness.
Specs
Procurement specifications
The table helps qualify the request quickly. For a commercial offer we verify datasheet, OEM SKU, availability and warranty region.
| GPU | 8x NVIDIA H100 / H200 class GPUs |
|---|---|
| GPU memory | up to 1 128 GB total on DGX H200 |
| Form factor | 8U rackmount class |
| Weight | about 130 kg class |
| Power | six 3.3 kW PSU class / ~10.2 kW max for DGX H200 |
| Workloads | enterprise AI training / inference / DGX platform |
RFQ
What to verify before quoting
- rack, floor load, depth and placement;
- power, PDU, redundancy and heat output;
- cooling: reinforced air conditioning or liquid loop depending on project;
- networking, storage, support and commissioning.
Critical limitation
NVIDIA DGX H100 / H200
DGX should not be installed like a common server. A prepared server room, industrial power, cooling, networking and operations plan are required.
Specification sources
The table helps qualify the request quickly. For a commercial offer we verify datasheet, OEM SKU, availability and warranty region.
Internal links
Related NVIDIA pages
These links keep model-level pages inside the current catalog architecture without overloading the global menu.
RFQ
Request price and availability
Attach SKU, BOM or model list. For server systems, include site, power, cooling, network and compatible server details.