Tesla K8 and GeForce RTX 4070 Ti SUPER - video card comparison

Tesla K8

GeForce RTX 4070 Ti SUPER

Architecture

Kepler (2012−2018)

Ada Lovelace

GPU code name

GK104

AD103-275

Market segment

Workstation

Desktop

Release date

September 2014

January 2024

Interface

PCIe 2.0 x16

PCIe 4.0 x16

Supplementary power connectors

1x 6-pin

1x 16-pin

Boost clock speed

811 MHz

2610 MHz

Core clock speed

693 MHz

2340 MHz

Floating-point performance

2,491 gflops

Manufacturing process technology

28 nm

5 nm

Number of transistors

3,540 million

45,900 million

Pipelines / CUDA cores

1536

8448

Power consumption (TDP)

100 Watt

285 Watt

Texture fill rate

103.8

689.0

Memory type

GDDR5

GDDR6X

Maximum RAM amount

8 GB

16 GB

Memory bus width

256 Bit

Memory clock speed

5000 MHz

21000 MHz

Memory bandwidth

160.0 GB/s

716.8 GB/s

Shared memory

Display Connectors

No outputs

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

DirectX

12 (11_0)

12 Ultimate (12_2)

CUDA

3.0

8.9

OpenCL

1.2

3.0

OpenGL

4.6

Shader Model

5.1

6.7

Vulkan

1.1.126

1.3