GeForce GTX 490 and GeForce RTX 3070 Ti - video card comparison

GeForce GTX 490

GeForce RTX 3070 Ti

Architecture

Fermi (2010−2014)

Ampere (2020−2022)

GPU code name

GF100

Ampere GA104

Market segment

Desktop

Release date

May 2021

Interface

PCIe 2.0 x16

PCIe 4.0 x16

Supplementary power connectors

2x 8-pin

1x 12-pin

Boost clock speed

1770 MHz

Core clock speed

608 MHz

1575 MHz

Manufacturing process technology

40 nm

8 nm

Number of transistors

3,100 million

17,400 million

Pipelines / CUDA cores

480

6144

Power consumption (TDP)

365 Watt

290 Watt

Texture fill rate

36.48

339.8

Memory type

GDDR5

GDDR6X

Maximum RAM amount

1536 MB

8 GB

Memory bus width

384 Bit

256 Bit

Memory clock speed

3.4 GB/s

19000 MHz

Memory bandwidth

164.0 GB/s

608.3 GB/s

Shared memory

Display Connectors

3x DVI, 1x mini-DisplayPort

1x HDMI, 3x DisplayPort

HDMI

DirectX

12 (11_0)

12 Ultimate (12_2)

CUDA

2.0

8.6

OpenCL

1.1

3.0

OpenGL

4.6

Shader Model

5.1

6.6

Vulkan

N/A

1.2