Tesla K80 and GeForce RTX 4090 Ti - video card comparison

Tesla K80

GeForce RTX 4090 Ti

Architecture

Kepler 2.0 (2013−2015)

Ada Lovelace

GPU code name

GK210

AD102

Market segment

Workstation

Desktop

Release date

November 2014

2023

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

1x 8-pin

2x 16-pin

Boost clock speed

824 MHz

2565 MHz

Core clock speed

562 MHz

Manufacturing process technology

28 nm

5 nm

Number of transistors

7,100 million

76,300 million

Pipelines / CUDA cores

2496

18176

Power consumption (TDP)

300 Watt

600 Watt

Texture fill rate

171.4

1,457

Memory type

GDDR5

GDDR6X

Maximum RAM amount

12 GB

24 GB

Memory bus width

384 Bit

Memory clock speed

5012 MHz

24 GB/s

Memory bandwidth

240.6 GB/s

1,152 GB/s

Display Connectors

No outputs

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

DirectX

12 (11_1)

12 Ultimate (12_2)

CUDA

3.7

8.9

OpenCL

1.2

3.0

OpenGL

4.6

Shader Model

5.1

6.7

Vulkan

1.1.126

1.3