DGX Blackwell / AI Factory

NVIDIA DGX B200

DGX B200 is a complete Blackwell system for AI factories. Quotes start with site readiness: power, cooling, rack, networking, storage and service plan.

Specs

Procurement specifications

The table helps qualify the request quickly. For a commercial offer we verify datasheet, OEM SKU, availability and warranty region.

GPU8x NVIDIA Blackwell GPUs
GPU memory1 440 GB HBM3e total
CPU2x Intel Xeon Platinum 8570
Form factor10 RU
Power usage~14.3 kW max
NVLink14.4 TB/s aggregate bandwidth

Procurement profile

Where this model makes sense

Designed for large AI projects, training and inference where full-stack software, support and predictable deployment matter.

  • large enterprise AI projects;
  • LLM training/inference and AI factories;
  • DGX SuperPOD and BasePOD scenarios.

RFQ

What to verify before quoting

  • 10 RU placement, rack depth and floor load;
  • ~14.3 kW max power, PDU and redundancy;
  • cooling for high heat output;
  • InfiniBand/Ethernet, storage, support and commissioning.

Critical limitation

NVIDIA DGX B200

DGX B200 requires industrial power, prepared rack infrastructure and engineered cooling. Without site checks, a commercial offer will be inaccurate.

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.

Back to section

RFQ

Request price and availability

Attach SKU, BOM or model list. For server systems, include site, power, cooling, network and compatible server details.