GeForce RTX 3090 SUPER and GeForce RTX 4090 Max-Q - video card comparison

GeForce RTX 3090 SUPER

GeForce RTX 4090 Max-Q

Architecture

Ampere (2020−2022)

Ada Lovelace

GPU code name

GA102

AD103

Market segment

Desktop

Release date

January 2023

Interface

PCIe 4.0 x16

Supplementary power connectors

1x 12-pin

None

Boost clock speed

1695 MHz

1455 MHz

Manufacturing process technology

8 nm

4 nm

Number of transistors

28,300 million

45,900 million

Pipelines / CUDA cores

10752

9728

Power consumption (TDP)

400 Watt

80 Watt

Texture fill rate

569.5

442.3

Memory type

GDDR6X

GDDR6

Maximum RAM amount

24 GB

16 GB

Memory bus width

384 Bit

256 Bit

Memory clock speed

21.2 GB/s

14 GB/s

Memory bandwidth

1,018 GB/s

448.0 GB/s

Display Connectors

1x HDMI, 3x DisplayPort

Portable Device Dependent

HDMI

DirectX

12 Ultimate (12_2)

CUDA

8.6

8.9

OpenCL

3.0

OpenGL

4.6

Shader Model

6.6

6.7

Vulkan

1.2

1.3