RTX PRO 6000 Server Edition GPUs | RTX-PRO-6000-BSE
Fast Shipping
100k+ SKUs
8/5 Support
Certified
NVIDIA RTX PRO 6000 Blackwell Server Edition | 96GB GDDR7
NVIDIA RTX PRO 6000 Blackwell Server Edition 96GB GDDR7 GPU
The NVIDIA RTX PRO 6000 Blackwell Server Edition is a data center GPU built for AI inference, generative AI, physical AI, scientific computing, rendering, visualization, and enterprise accelerated workloads. With 96GB of GDDR7 ECC memory, PCIe Gen 5 connectivity, fifth-generation Tensor Cores, fourth-generation RT Cores, and a passive data center thermal design, this GPU is made for supported enterprise server platforms.
This Server Edition is designed for multi-GPU rackmount servers where chassis airflow provides cooling across passive heatsinks. It is a strong fit for organizations building RTX PRO servers, AI inference systems, high-density visualization platforms, and GPU-accelerated data center infrastructure.
Availability may vary by NVIDIA channel SKU, OEM SKU, server manufacturer part number, and system configuration. For current availability, server compatibility, GPU quantity planning, or complete system configuration support, please contact Catalyst Data Solutions.
End-user / export compliance notice: Advanced AI accelerators and systems may be subject to applicable U.S. export controls, end-user/end-use restrictions, destination requirements, and OEM/channel policies. Catalyst may request purchaser, final end-user, intended-use, and deployment-location information before a quote or fulfillment can be approved. An RFQ does not guarantee allocation or shipment.
Technical Specifications
| Product Family | NVIDIA RTX PRO 6000 Blackwell |
|---|---|
| Edition | Server Edition |
| GPU Architecture | NVIDIA Blackwell |
| CUDA Cores | 24,064 |
| GPU Memory | 96GB GDDR7 with ECC |
| Memory Interface | 512-bit |
| Memory Bandwidth | 1,597 GB/s |
| System Interface | PCIe 5.0 x16 |
| Display Connectors | 4x DisplayPort 2.1 |
| Power Consumption | Up to 600W configurable |
| Thermal Solution | Passive; air- and liquid-cooled server designs |
| Form Factor | 4.4” H x 10.5” L, dual slot |
SKU / Part Number Variants
| SKU / Part Number | Variant Type |
|---|---|
| 900-2G153-0010-000 | NVIDIA standard passive base SKU |
| 900-2G153-2200-001 | Channel distribution / retail variant |
| 900-2G153-2700-030 | Specialized data center cluster variant |
| RTXPRO6000TC | Generic server inventory identifier |
| PNY NVRTXPRO6000TCGPU-KIT | PNY server-qualified ecosystem kit |
| S6A73C | HPE server accelerator SKU |
| 900-5G153-0100-000-DELL | Dell system-specific ordering identifier |
Data Sheet
📂 RTX PRO 6000 Blackwell Server Edition Data Sheet
Workload Benefits & Common Use Cases
- Enterprise AI inference: 96GB GDDR7 ECC memory and Blackwell Tensor Cores support multimodal AI, generative AI, and production inference workloads.
- RTX PRO server deployments: The passive thermal design makes this GPU suitable for rackmount server environments with chassis-driven airflow.
- Physical AI and simulation: Strong AI and RT performance supports robotics simulation, digital twins, and industrial visualization workflows.
- Rendering and visualization at scale: Data center GPU deployments can accelerate remote visualization, virtual workstations, 3D graphics, and rendering pipelines.
- HPC and scientific computing: PCIe Gen 5, large memory, and enterprise GPU reliability support accelerated research and compute workloads.
- Multi-tenant GPU usage: MIG support helps divide a single GPU into isolated instances for concurrent workloads and improved utilization.
Compatibility & Popular Deployment Environments
The RTX PRO 6000 Blackwell Server Edition is commonly deployed in supported enterprise servers with passive GPU airflow, validated PCIe Gen 5 slots, proper power delivery, qualified firmware, and sufficient thermal design.
Popular Deployment Environments
- AI inference servers
- RTX PRO server platforms
- Data center GPU compute nodes
- Remote visualization and virtual workstation infrastructure
- HPC and scientific computing clusters
- Enterprise AI factories and private cloud GPU environments
Frequently Paired Components
- Dell, HPE, Lenovo, Supermicro, and NVIDIA-Certified server platforms
- High-core-count server CPUs
- DDR5 server memory
- NVMe enterprise storage
- 100G, 200G, or 400G Ethernet networking
- InfiniBand networking for distributed GPU workloads
- High-wattage redundant power supplies
Frequently Asked Questions
What is the RTX PRO 6000 Blackwell Server Edition used for?
It is used for enterprise AI inference, generative AI, physical AI, scientific computing, remote visualization, rendering, and accelerated data center workloads.
How is the Server Edition different from the Workstation Edition?
The Server Edition uses a passive thermal design intended for rackmount servers with chassis-driven airflow. The Workstation Edition is designed for desktop workstation systems.
Is this GPU compatible with any server?
No. It should only be installed in server platforms validated for RTX PRO 6000 Blackwell Server Edition GPUs, with proper PCIe support, power delivery, firmware, and cooling.
| Memory Capacity | 96GB |
|---|---|
| Interface | PCIe |
| Condition | New |
| product series | Workstation Edition |
