Radeon HD 5670 and GeForce RTX 3060 Ti GA103 - video card comparison

Radeon HD 5670

GeForce RTX 3060 Ti GA103

Architecture

Terascale 2 (2009−2015)

Ampere (2020−2022)

GPU code name

Redwood

GA103S

Market segment

Desktop

Release date

January 2010

February 2022

Interface

PCIe 2.0 x16

PCIe 4.0 x16

Supplementary power connectors

None

1x 12-pin

Boost clock speed

1665 MHz

Core clock speed

775 MHz

Floating-point performance

620.0 gflops

Manufacturing process technology

40 nm

8 nm

Number of transistors

627 million

Pipelines / CUDA cores

400

4864

Power consumption (TDP)

64 Watt

200 Watt

Texture fill rate

15.50

253.1

Memory type

GDDR5

GDDR6

Maximum RAM amount

1 GB

8 GB

Memory bus width

128 Bit

256 Bit

Memory clock speed

1000 MHz

14 GB/s

Memory bandwidth

64 GB/s

448.0 GB/s

Display Connectors

1x DVI, 1x HDMI, 1x VGA

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

DirectX

11.2 (11_0)

12 Ultimate (12_2)

CUDA

8.6

OpenCL

1.2

3.0

OpenGL

4.4

4.6

Shader Model

5.0

6.5

Vulkan

N/A

1.3