RTX PRO 4000 Blackwell SFF vs CMP 90HX

#ad 
Buy on Amazon
VS

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the rankingnot ratednot rated
Place by popularitynot in top-100not in top-100
ArchitectureAmpere (2020−2025)Blackwell 2.0 (2025)
GPU code nameGA102GB203
Market segmentWorkstationWorkstation
Release date28 July 2021 (4 years 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 cores64008960
Core clock speed1500 MHz790 MHz
Boost clock speed1710 MHz1337 MHz
Number of transistors28,300 million45,600 million
Manufacturing process technology8 nm5 nm
Power consumption (TDP)320 Watt70 Watt
Texture fill rate342.0374.4
Floating-point processing power21.89 TFLOPS23.96 TFLOPS
ROPs8096
TMUs200280
Tensor Cores200280
Ray Tracing Cores5070

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).

InterfacePCIe 1.0 x4PCIe 5.0 x8
Length285 mm167 mm
Width2-slot1-slot
Supplementary power connectors2x 8-pinNone

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 typeGDDR6XGDDR7
Maximum RAM amount10 GB24 GB
Memory bus width320 Bit192 Bit
Memory clock speed1188 MHz1125 MHz
Memory bandwidth760.3 GB/s432.0 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 ConnectorsNo outputs4x mini-DisplayPort 2.1b

API and SDK compatibility

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX12 Ultimate (12_2)12 Ultimate (12_2)
Shader Model6.86.8
OpenGL4.64.6
OpenCL3.03.0
Vulkan1.31.4
CUDA8.612.0
DLSS++

Pros & cons summary


Recency 28 July 2021 11 August 2025
Maximum RAM amount 10 GB 24 GB
Chip lithography 8 nm 5 nm
Power consumption (TDP) 320 Watt 70 Watt

RTX PRO 4000 Blackwell SFF has an age advantage of 4 years, a 140% higher maximum VRAM amount, a 60% more advanced lithography process, and 357.1% lower power consumption.

We couldn't decide between CMP 90HX and RTX PRO 4000 Blackwell SFF. We've got no test results to judge.

Vote for your favorite

Do you think we are right or mistaken in our choice? Vote by clicking "Like" button near your favorite graphics card.


NVIDIA CMP 90HX
CMP 90HX
NVIDIA RTX PRO 4000 Blackwell SFF
RTX PRO 4000 Blackwell SFF

Other comparisons

We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.

Community ratings

Here you can see the user ratings of the compared graphics cards, as well as rate them yourself.


4.6 48 votes

Rate CMP 90HX on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

No user ratings yet.

Rate RTX PRO 4000 Blackwell SFF on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Comments

Here you can give us your opinion about CMP 90HX or RTX PRO 4000 Blackwell SFF, agree or disagree with our ratings, or report errors or inaccuracies on the site.