RTX PRO 4000 Blackwell SFF vs GeForce RTX 5090 D
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 1 | not rated |
| Place by popularity | 9 | not in top-100 |
| Power efficiency | 13.25 | no data |
| Architecture | Blackwell 2.0 (2025) | Blackwell 2.0 (2025) |
| GPU code name | GB202 | GB203 |
| Market segment | Desktop | Workstation |
| Release date | 30 January 2025 (less than a year ago) | 11 August 2025 (recently) |
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 21760 | 8960 |
| Core clock speed | 2017 MHz | 790 MHz |
| Boost clock speed | 2407 MHz | 1337 MHz |
| Number of transistors | 92,200 million | 45,600 million |
| Manufacturing process technology | 5 nm | 5 nm |
| Power consumption (TDP) | 575 Watt | 70 Watt |
| Texture fill rate | 1,637 | 374.4 |
| Floating-point processing power | 104.8 TFLOPS | 23.96 TFLOPS |
| ROPs | 176 | 96 |
| TMUs | 680 | 280 |
| Tensor Cores | 680 | 280 |
| Ray Tracing Cores | 170 | 70 |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Interface | PCIe 5.0 x16 | PCIe 5.0 x8 |
| Length | 304 mm | 167 mm |
| Width | 2-slot | 1-slot |
| Supplementary power connectors | 1x 16-pin | None |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR7 | GDDR7 |
| Maximum RAM amount | 32 GB | 24 GB |
| Memory bus width | 512 Bit | 192 Bit |
| Memory clock speed | 1750 MHz | 1125 MHz |
| Memory bandwidth | 1.79 TB/s | 432.0 GB/s |
| Resizable BAR | + | + |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | 1x HDMI 2.1b, 3x DisplayPort 2.1b | 4x mini-DisplayPort 2.1b |
| HDMI | + | - |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.8 | 6.8 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.4 | 1.4 |
| CUDA | 10.1 | 12.0 |
| DLSS | + | + |
Pros & cons summary
| Recency | 30 January 2025 | 11 August 2025 |
| Maximum RAM amount | 32 GB | 24 GB |
| Power consumption (TDP) | 575 Watt | 70 Watt |
RTX 5090 D has a 33.3% higher maximum VRAM amount.
RTX PRO 4000 Blackwell SFF, on the other hand, has an age advantage of 6 months, and 721.4% lower power consumption.
We couldn't decide between GeForce RTX 5090 D and RTX PRO 4000 Blackwell SFF. We've got no test results to judge.
Be aware that GeForce RTX 5090 D is a desktop graphics card while RTX PRO 4000 Blackwell SFF is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
