Radeon Pro VII and GeForce RTX 4070 - video card comparison

Passmark - benchmark score Radeon Pro VII vs GeForce RTX 4070

Radeon Pro VII

13110

GeForce RTX 4070

27788

Radeon Pro VII

GeForce RTX 4070

Architecture

GCN 5.1 (2018−2021)

Ada Lovelace

GPU code name

Vega 20

AD104

Market segment

Workstation

Desktop

Release date

May 2020

April 2023

Interface

PCIe 4.0 x16

Supplementary power connectors

1x 6-pin + 1x 8-pin

1x 16-pin

Boost clock speed

1700 MHz

2475 MHz

Core clock speed

1920 MHz

Manufacturing process technology

7 nm

5 nm

Number of transistors

13,230 million

35,800 million

Pipelines / CUDA cores

3840

5888

Power consumption (TDP)

250 Watt

200 Watt

Texture fill rate

408.0

455.4

Memory type

HBM2

GDDR6X

Maximum RAM amount

16 GB

12 GB

Memory bus width

4096 Bit

192 Bit

Memory clock speed

2 GB/s

21000 MHz

Memory bandwidth

1024 GB/s

504.2 GB/s

Shared memory

Display Connectors

6x mini-DisplayPort 1.4a

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

DirectX

12 (12_1)

12 Ultimate (12_2)

CUDA

8.9

OpenCL

2.1

3.0

OpenGL

4.6

Shader Model

6.7

Vulkan

1.3