NVIDIA RTX PRO 4000 Blackwell SFF: specs and benchmarks
Contents
Summary
NVIDIA started RTX PRO 4000 Blackwell SFF sales 11 August 2025. This is a Blackwell 2.0 architecture desktop card based on 5 nm manufacturing process and primarily aimed at designers. 24 GB of GDDR7 memory clocked at 1.13 GHz are supplied, and together with 192 Bit memory interface this creates a bandwidth of 432.0 GB/s.
Compatibility-wise, this is a single-slot graphics card attached via PCIe 5.0 x8 interface. Its manufacturer default version has a length of 167 mm. No additional power connector is required, and power consumption is at 70 Watt.
Primary details
Some basic facts about RTX PRO 4000 Blackwell SFF: architecture, market segment, release date etc.
| Place in the ranking | not rated | |
| Place by popularity | not in top-100 | |
| Architecture | Blackwell 2.0 (2025) | |
| GPU code name | GB203 | |
| Market segment | Workstation | |
| Release date | 11 August 2025 (recently) |
Detailed specifications
RTX PRO 4000 Blackwell SFF's specs such as number of shaders, GPU base clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of RTX PRO 4000 Blackwell SFF's performance, but for precise assessment you have to consider its benchmark and gaming test results.
| Pipelines / CUDA cores | 8960 | of 24064 (RTX PRO 6000 Blackwell) |
| Core clock speed | 790 MHz | of 2670 MHz (Arc B580) |
| Boost clock speed | 1337 MHz | of 3230 MHz (Radeon RX 9060 XT) |
| Number of transistors | 45,600 million | of 185,000 million (Radeon Instinct MI350X) |
| Manufacturing process technology | 5 nm | of 3 nm (Arc Graphics 140V) |
| Power consumption (TDP) | 70 Watt | of 2400 Watt (Data Center GPU Max Subsystem) |
| Texture fill rate | 374.4 | of 2,554 (Radeon Instinct MI300X) |
| Floating-point processing power | 23.96 TFLOPS | of 126 (RTX PRO 6000 Blackwell) |
| ROPs | 96 | of 512 (Moore Threads MTT S4000) |
| TMUs | 280 | of 1280 (Data Center GPU Max NEXT) |
| Tensor Cores | 280 | of 1216 (Radeon Instinct MI300X) |
| Ray Tracing Cores | 70 | of 188 (RTX PRO 6000 Blackwell) |
Form factor & compatibility
This section provides details about the physical dimensions of RTX PRO 4000 Blackwell SFF and its compatibility with other computer components. This information is useful when selecting a computer configuration or upgrading an existing one. For desktop graphics cards, it includes details about the interface and bus (for motherboard compatibility) and additional power connectors (for power supply compatibility).
| Interface | PCIe 5.0 x8 | |
| Length | 167 mm | |
| Width | 1-slot | |
| Supplementary power connectors | None |
VRAM capacity and type
Parameters of memory installed on RTX PRO 4000 Blackwell SFF: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors have no dedicated memory and use a shared part of system RAM instead.
| Memory type | GDDR7 | |
| Maximum RAM amount | 24 GB | of 288 GB (Radeon Instinct MI325X) |
| Memory bus width | 192 Bit | of 8192 Bit (Radeon Instinct MI250X) |
| Memory clock speed | 1125 MHz | of 16000 GB/s (GeForce RTX 4050 Mobile) |
| Memory bandwidth | 432.0 GB/s | of 5,171 GB/s (Radeon Instinct MI300X) |
| Resizable BAR | + |
Connectivity and outputs
Types and number of video connectors present on RTX PRO 4000 Blackwell SFF. As a rule, this section is relevant only for desktop reference graphics cards, since for notebook ones the availability of certain video outputs depends on the laptop model, while non-reference desktop models can (though not necessarily will) bear a different set of video ports.
| Display Connectors | 4x mini-DisplayPort 2.1b |
API and SDK compatibility
APIs supported by RTX PRO 4000 Blackwell SFF, sometimes including their particular versions.
| DirectX | 12 Ultimate (12_2) | |
| Shader Model | 6.8 | |
| OpenGL | 4.6 | |
| OpenCL | 3.0 | |
| Vulkan | 1.4 | |
| CUDA | 12.0 | |
| DLSS | + |
AMD equivalent
According to our data, the closest AMD alternative to RTX PRO 4000 Blackwell SFF is Radeon Pro W6900X.
Similar GPUs
Here is our recommendation of several graphics cards that are more or less close in performance to the one reviewed.
