NVIDIA RTX PRO 6000 Blackwell Server Edition GPU
NVIDIA RTX PRO 6000 Blackwell Server Edition as a single card, 96 GB GDDR7 ECC, 24,064 CUDA cores, passive dual slot, 400 to 600 W, for validated servers.
- Memory
- 96 GB GDDR7 with ECC, 1.6 TB/s
- Compute
- 24,064 CUDA cores, fifth generation Tensor cores, 4 PFLOPS FP4
- Power
- 400 W to 600 W configurable
- Form factor
- Dual slot full height full length, passive; single slot liquid cooled variant
- Features
- MIG up to 4 instances, 4 x NVENC and 4 x NVDEC, PCIe Gen5 x16
- Registration
- NVIDIA end user registration and export controls apply
Overview
The server edition card is supplied individually for customers who add GPUs to servers they already own, standardize on a card for several builders, or hold spares for an inference fleet. It carries the full RTX PRO 6000 Blackwell specification, with 96 GB of GDDR7 with ECC, 24,064 CUDA cores and 4 PFLOPS of FP4, in a passive dual slot package that depends on chassis airflow.
Because it is passive and draws up to 600 W, it only belongs in servers validated for that class of GPU. We check the server model, power supply and airflow before shipping a card and can configure the power limit to 400 W for chassis with less cooling headroom. A single slot liquid cooled variant exists for direct liquid cooled servers.
Data center GPUs are subject to NVIDIA end user registration and US export controls, so we collect end user and deployment country details with the quotation and handle registration with the order. Volume quotations follow NVIDIA allocation at the time of order.
Use cases
- Adding GPUs to validated servers
- Fleet spares
- Standardizing a GPU across builders
- Liquid cooled server builds
Specifications
| Architecture | NVIDIA Blackwell |
|---|---|
| CUDA cores | 24,064 |
| Tensor cores | Fifth generation, 4 PFLOPS FP4, 2 PFLOPS FP8 |
| RT cores | 188 fourth generation |
| Memory | 96 GB GDDR7 with ECC, 512 bit, 1,597 GB/s |
| Form factor | Dual slot FHFL air cooled; single slot FHXL liquid cooled |
|---|---|
| Cooling | Passive, requires server airflow validated for 600 W GPUs |
| Power | Up to 600 W configurable, 400 W minimum |
| Interface | PCIe Gen5 x16 |
| Multi Instance GPU | Up to 4 instances |
|---|---|
| Media | 4 x ninth generation NVENC, 4 x sixth generation NVDEC |
| Displays | 4 x DisplayPort 2.1 |
Figures describe the system class. Exact configuration, weights and power draw are confirmed on the quotation.
What's included
- Original manufacturer part in retail or bulk packaging
- Compatibility check against your server or workstation model
- Manufacturer warranty passed through, advance replacement options
- NVIDIA end user registration handled with the order
Compliance
Related
Related systems
8 GPU RTX PRO 6000 PCIe AI server
- GPUs
- 8 x RTX PRO 6000 Blackwell Server Edition
- CPU
- 2 x AMD EPYC 9005 or 2 x Intel Xeon 6
- Memory
- Up to 2 TB DDR5 RDIMM
- Chassis
- 4U, about 6.5 kW, air cooled
RTX PRO 6000 Blackwell workstation GPU
- Memory
- 96 GB GDDR7 with ECC, 1.8 TB/s
- Compute
- 24,064 CUDA cores
- Editions
- Workstation Edition 600 W double flow through
- Form factor
- Dual slot, PCIe Gen5 x16
NVIDIA H200 NVL GPU
Available on request- Memory
- 141 GB HBM3e, 4.8 TB/s
- Compute
- Hopper, 3,341 TFLOPS sparse FP8
- Interconnect
- 2 way or 4 way NVLink bridge at 900 GB/s per GPU
- Power
- Up to 600 W configurable
4 GPU PCIe AI server, 2U
- GPUs
- 4 x RTX PRO 6000 Blackwell Server Edition
- CPU
- 2 x AMD EPYC 9005 or 2 x Intel Xeon 6
- Memory
- Up to 1.5 TB DDR5 RDIMM
- Chassis
- 2U, about 3.5 kW, air cooled
Related guides
Buying data center GPUs, export and registration
The compliance steps that come with every HGX, H200 NVL, Server Edition and NVL72 purchase, explained so your order ships on time.
In this guide
- Why a GPU purchase comes with paperwork
- Which products are covered
Choosing a GPU server for LLM inference
A practical method for sizing an inference server from the model, the quantization and the concurrency you expect, with worked examples.
In this guide
- Start with the model, not the server
- Step 1: how much GPU memory the weights need
HGX vs PCIe GPU servers
The real differences between an HGX node and a PCIe GPU server, and a simple rule for choosing between them.
In this guide
- Two kinds of 8 GPU server
- The interconnect is the point
How to request a quotation
A short guide to getting a complete, accurate quotation, from the details we need to what the quotation contains.
In this guide
- Why there are no prices on this site
- Three ways to ask
Compare it with the next class up or down
The nearest classes we quote are the 8 GPU RTX PRO 6000 PCIe AI server and the RTX PRO 6000 Blackwell workstation GPU. If neither is quite right, tell us the workload and we specify the system between them.
- (858) 613-1818
- sales@computermodules.com
- Monday to Friday, 8am to 5pm Pacific