Radeon Pro 575 and GeForce RTX 4060 Ti - video card comparison

Radeon Pro 575

GeForce RTX 4060 Ti

Architecture

GCN 4.0 (2016−2020)

Ada Lovelace

GPU code name

Polaris 20

AD106

Market segment

Mobile workstation

Desktop

Release date

June 2017

May 2023

Interface

PCIe 3.0 x16

PCIe 4.0 x8

Supplementary power connectors

None

1x 16-pin

Boost clock speed

2535 MHz

Core clock speed

1096 MHz

Floating-point performance

4,506 gflops

Manufacturing process technology

14 nm

5 nm

Number of transistors

5,700 million

22,900 million

Pipelines / CUDA cores

2048

4352

Power consumption (TDP)

120 Watt

160 Watt

Texture fill rate

140.3

344.8

Memory type

GDDR5

GDDR6

Maximum RAM amount

4 GB

8 GB

Memory bus width

256 Bit

128 Bit

Memory clock speed

6780 MHz

18 GB/s

Memory bandwidth

217.0 GB/s

288.0 GB/s

Display Connectors

No outputs

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

DirectX

12 (12_0)

12 Ultimate (12_2)

CUDA

8.9

OpenCL

2.0

3.0

OpenGL

4.6

Shader Model

6.4

6.7

Vulkan

1.2.131

1.3