MPN: RTXPRO4000·By: NVIDIA
Ships from the US.
We'll confirm availability and pricing for RTXPRO4000, usually within one business day.
We'll confirm availability and pricing for RTXPRO4000, usually within one business day.
The NVIDIA RTX PRO 4000 Blackwell is a workstation graphics card built on the NVIDIA Blackwell architecture and identified by SKU RTXPRO4000. It is equipped with 24 GB of GDDR7 memory with ECC and uses a PCIe 5.0 x16 system interface. The card is listed with 8,960 CUDA cores and 4th generation ray tracing cores, along with 5th generation Tensor cores. Display connectivity includes four DisplayPort 2.1 connectors. The product is described as a professional desktop graphics card in the workstation category. Power consumption is specified at 140 W total board power. The available form factor data indicates a single-slot, full-height design. These specifications make it a fit for procurement teams evaluating professional GPU deployment where Blackwell architecture, 24 GB memory capacity, and PCIe 5.0 connectivity are required.
| Manufacturer part # | RTXPRO4000 |
|---|---|
| Brand | NVIDIA |
| Condition | New |
| Model | RTX PRO 4000 Blackwell |
| CUDA Cores | 8,960 |
| GPU memory | 24 GB GDDR7 with ECC |
| Technology | Blackwell |
| Form factor | single slot, full height |
| Compute APIs | CUDA 12.8, OpenCL 3.0, DirectCompute |
| Product Line | RTX PRO |
| Product Type | GPU |
| Tensor Cores |
Confirmed as an NVIDIA RTX PRO 4000 Blackwell workstation GPU with PCIe 5.0 x16 and 24 GB GDDR7 ECC.
Built for workstation use, this GPU is specified as a professional desktop graphics card. Its Blackwell architecture and 24 GB GDDR7 memory support professional deployment requirements.
The card includes four DisplayPort 2.1 connectors. That interface count supports display-focused workstation configurations that require multiple direct monitor connections.
The system interface is PCIe 5.0 x16. This makes the card suitable for platforms that are built to use PCIe 5.0 graphics expansion.
The card includes 24 GB of GDDR7 memory with ECC. That memory specification is relevant for workflows that need substantial GPU memory capacity.
Details
Shipping, warranty & returns
No reviews yet — be the first to review this part.
Secure SSL checkout. Visa, Mastercard, Amex and Discover accepted. ACH / wire available for businesses.
New, certified-refreshed and OEM stock with guaranteed compatibility, backed by warranty on every part.
We process quotes, POs, stock documentation and compliance invoicing.
[email protected]| 5th Generation |
| Graphics APIs | DirectX 12, Shader Model 6.6, OpenGL 4.6, Vulkan 1.3 |
|---|
| Video Engines | 2x NVENC, 2x NVDEC |
|---|
| AI Performance | 1178 AI TOPS |
|---|
| GPU architecture | NVIDIA Blackwell |
|---|
| Thermal solution | Active |
|---|
| Ray Tracing Cores | 4th Generation |
|---|
| Total board power | 145 W |
|---|
| Display connectors | 4x DisplayPort 2.1b |
|---|
| RT Core Performance | 112 TFLOPS |
|---|
| Max simultaneous displays | 4x 3840 x 2160 @ 165 Hz, 2x 7680 x 4320 @ 100 Hz |
|---|
| Single-Precision Performance | 37 TFLOPS |
|---|
| Memory bandwidth | 672 GB/s |
|---|
| Power consumption | 145 W |
|---|---|
| Max Power Consumption | 145 W |
| PCIe Version | 5.0 x16 |
|---|---|
| Connector Count | 4 |
| Power Connector | 1x PCIe CEM5 16-pin |
| Memory interface | 192-bit |
| System interface | PCIe 5.0 x16 |
| DisplayPort Ports | 4 |
| DisplayPort Version | 2.1b |
The card is built on NVIDIA Blackwell architecture. It is listed as a workstation product and a professional desktop graphics card, so the architecture information is the main generation identifier in the provided specifications.
The RTX PRO 4000 Blackwell includes 24 GB of GDDR7 memory with ECC. That is the only memory configuration specified in the provided data, and it is the key capacity detail for planning workstation deployments.
The system interface is PCIe 5.0 x16. This is the host connection specification given in the product data, and it is important for checking compatibility with workstation motherboards that support PCIe 5.0 graphics slots.
The card has four DisplayPort 2.1 connectors. That connector count is the only display interface detail provided, and it supports multi-monitor workstation setups that require direct GPU-connected displays.
The provided data lists 140 W total board power. This is the key power planning figure for the card, and it should be used when evaluating workstation power budgets and chassis-level electrical requirements.
The product data lists 8,960 CUDA cores, 5th generation Tensor cores, and 4th generation Ray Tracing cores. These are the only compute-related specifications provided, so buyers can use them as the documented performance indicators for comparison.
You might also want to check out these products.

900-2H403-0000-000 - Nvidia Tesla P100 16GB HBM2 NVlink SXM2 GPU

900-22081-0040-000 - NVIDIA Tesla K40 Video Graphic Card

100-506115 - AMD Radeon Pro WX 3200 Graphic Card 4GB GDDR5

900-1G611-2530-000 - Nvidia TITAN Xp 12GB GDDR5X Graphics Card

900-52055-0310-000 - NVIDIA Tesla Grid K2 8GB Video Graphics Card

900-2G183-0000-001 - Nvidia Tesla T4 Turing 16GB GDDR6 PCIe x16 GPU

699-2G402-0060-300 - NVIDIA Tesla M60 16GB GDDR5 Video Graphics Card

900-22081-0110-000 - NVIDIA Tesla K20 5GB GDDR5 320-Bit GPU