CMP 170HX vs Radeon Instinct MI25

Primary details

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

Place in the ranking389not rated
Place by popularitynot in top-100not in top-100
Power efficiency3.00no data
ArchitectureGCN 5.0 (2017−2020)Ampere (2020−2024)
GPU code nameVega 10GA100
Market segmentWorkstationWorkstation
Release date27 June 2017 (7 years ago)1 September 2021 (3 years ago)
Launch price (MSRP)no data$4,299

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 cores40964480
Core clock speed1400 MHz1140 MHz
Boost clock speed1500 MHz1410 MHz
Number of transistors12,500 million54,200 million
Manufacturing process technology14 nm7 nm
Power consumption (TDP)300 Watt250 Watt
Texture fill rate384.0394.8
Floating-point processing power12.29 TFLOPS12.63 TFLOPS
ROPs64128
TMUs256280
Tensor Coresno data280

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 3.0 x16PCIe 4.0 x4
Length267 mmno data
Width2-slotIGP
Supplementary power connectors2x 8-pin2x 8-pin

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 typeHBM2HBM2e
Maximum RAM amount16 GB16 GB
Memory bus width2048 Bit4096 Bit
Memory clock speed852 MHz1458 MHz
Memory bandwidth436.2 GB/s1,493 GB/s

Connectivity and outputs

Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.

Display ConnectorsNo outputsNo outputs

API compatibility

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

DirectX12 (12_1)N/A
Shader Model6.4N/A
OpenGL4.6N/A
OpenCL2.03.0
Vulkan1.1.125N/A
CUDA-8.0

Pros & cons summary


Recency 27 June 2017 1 September 2021
Chip lithography 14 nm 7 nm
Power consumption (TDP) 300 Watt 250 Watt

CMP 170HX has an age advantage of 4 years, a 100% more advanced lithography process, and 20% lower power consumption.

We couldn't decide between Radeon Instinct MI25 and CMP 170HX. We've got no test results to judge.


Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.

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.


AMD Radeon Instinct MI25
Radeon Instinct MI25
NVIDIA CMP 170HX
CMP 170HX

Comparisons with similar GPUs

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 13 votes

Rate Radeon Instinct MI25 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
4 17 votes

Rate CMP 170HX on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Questions & comments

Here you can ask a question about this comparison, agree or disagree with our judgements, or report an error or mismatch.