H100 CNX and GeForce RTX 4070 SUPER - video card comparison

H100 CNX

GeForce RTX 4070 SUPER

Architecture

Hopper (2022)

Ada Lovelace

GPU code name

GH100

AD104

Market segment

Desktop

Release date

March 2023

January 2024

Interface

PCIe 5.0 x16

PCIe 4.0 x16

Supplementary power connectors

8-pin EPS

1x 16-pin

Boost clock speed

1845 MHz

2475 MHz

Core clock speed

1980 MHz

Manufacturing process technology

4 nm

5 nm

Number of transistors

80,000 million

35,800 million

Pipelines / CUDA cores

14592

7168

Power consumption (TDP)

350 Watt

220 Watt

Texture fill rate

841.3

584.6

Memory type

HBM2e

GDDR6X

Maximum RAM amount

80 GB

12 GB

Memory bus width

5120 Bit

192 Bit

Memory clock speed

3.2 GB/s

21000 MHz

Memory bandwidth

2,039 GB/s

504.2 GB/s

Shared memory

Display Connectors

No outputs

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

DirectX

N/A

12 Ultimate (12_2)

CUDA

9.0

8.9

OpenCL

3.0

OpenGL

N/A

4.6

Shader Model

N/A

6.7

Vulkan

N/A

1.3