GeForce RTX 4090 and CMP 170HX 8 GB - video card comparison

GeForce RTX 4090

CMP 170HX 8 GB

Architecture

Ada Lovelace

Ampere (2020−2022)

GPU code name

AD102-300-A1

GA100

Market segment

Desktop

Release date

September 2022

September 2021

Interface

PCIe 4.0 x16

PCIe 4.0 x4

Supplementary power connectors

1x 16-pin

2x 8-pin

Boost clock speed

2520 MHz

1410 MHz

Core clock speed

2235 MHz

Manufacturing process technology

5 nm

7 nm

Number of transistors

76,300 million

54,200 million

Pipelines / CUDA cores

16384

4480

Power consumption (TDP)

450 Watt

250 Watt

Texture fill rate

1,290

394.8

Memory type

GDDR6X

HBM2e

Maximum RAM amount

24 GB

8 GB

Memory bus width

384 Bit

4096 Bit

Memory clock speed

21000 MHz

2.9 GB/s

Memory bandwidth

1,008 GB/s

1,493 GB/s

Shared memory

Display Connectors

1x HDMI 2.1, 3x DisplayPort 1.4a

No outputs

HDMI

DirectX

12 Ultimate (12_2)

N/A

CUDA

8.9

8.0

OpenCL

3.0

OpenGL

4.6

N/A

Shader Model

6.6

N/A

Vulkan

1.3

N/A