RTX PRO Server / Enterprise AI

NVIDIA RTX PRO 6000 Blackwell Server Edition

Name: NVIDIA RTX PRO 6000 Blackwell Server Edition
Brand: NVIDIA

The server RTX PRO 6000 Blackwell is used for enterprise AI, industrial AI, visualization, simulation and workloads that need large GDDR7 ECC memory without moving directly to a full DGX/HGX rack.

Request price View specification

Specs

Procurement specifications

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

Architecture	NVIDIA Blackwell
CUDA cores	24 064
Memory	96 GB GDDR7 ECC
Bus / bandwidth	512-bit / 1 597 GB/s
Thermal solution	Air dual-slot FHFL / Liquid single-slot FHXL
Power	up to 600 W configurable
MIG	up to 4 isolated instances
Focus	Enterprise AI / rendering / simulation / visual computing

NVIDIA RTX PRO 6000 Blackwell Server Edition NVIDIA RTX PRO Server

Procurement profile

Where this model makes sense

Quotes are built around the OEM BOM: server, airflow, GPU count, NICs, DPUs, cabling, PSUs and warranty route.

LLM inference, agentic AI and enterprise AI platforms;
industrial AI, Omniverse, digital twins and rendering;
2U/4U/6U servers from Dell, HPE, Lenovo, Supermicro, ASUS, Gigabyte and other OEMs.

RFQ

What to verify before quoting

OEM server QVL and supported RTX PRO 6000 count per node;
airflow, air/liquid cooling, power budget and power cables;
MIG, vGPU, AI Enterprise and licensing requirements;
networking: ConnectX, BlueField, InfiniBand/Ethernet and cabling.

Critical limitation