A40 PCIe and GeForce RTX 5080 - video card comparison

A40 PCIe

GeForce RTX 5080

Architecture

Ampere (2020−2022)

Blackwell 2.0

GPU code name

GA102

GB203

Market segment

Desktop

Desktop

Release date

October 2020

2025 (recently)

Interface

PCIe 4.0 x16

PCIe 5.0 x16

Supplementary power connectors

8-pin EPS

1x 16-pin

Boost clock speed

1755 MHz

2520 MHz

Manufacturing process technology

8 nm

0 nm

Number of transistors

28,300 million

-

Pipelines / CUDA cores

10752

10752

Power consumption (TDP)

300 Watt

350 Watt

Texture fill rate

589.7

846.7

Memory type

GDDR6

GDDR7

Maximum RAM amount

48 GB

16 GB

Memory bus width

384 Bit

256 Bit

Memory clock speed

14.5 GB/s

5 GB/s

Memory bandwidth

695.8 GB/s

160.0 GB/s

Display Connectors

3x DisplayPort

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

-

+

DirectX

12 Ultimate (12_2)

12 Ultimate (12_2)

CUDA

8.6

9.1

OpenCL

2.0

3.0

OpenGL

4.6

4.6

Shader Model

6.5

6.7

Vulkan

1.2

1.3