GeForce RTX 4090 and H100 CNX - video card comparison

GeForce RTX 4090

H100 CNX

Architecture

Ada Lovelace

Hopper (2022)

GPU code name

AD102-300-A1

GH100

Market segment

Desktop

Desktop

Release date

September 2022

March 2023

Interface

PCIe 4.0 x16

PCIe 5.0 x16

Supplementary power connectors

1x 16-pin

8-pin EPS

Boost clock speed

2520 MHz

1845 MHz

Core clock speed

2235 MHz

-

Manufacturing process technology

5 nm

4 nm

Number of transistors

76,300 million

80,000 million

Pipelines / CUDA cores

16384

14592

Power consumption (TDP)

450 Watt

350 Watt

Texture fill rate

1,290

841.3

Memory type

GDDR6X

HBM2e

Maximum RAM amount

24 GB

80 GB

Memory bus width

384 Bit

5120 Bit

Memory clock speed

21000 MHz

3.2 GB/s

Memory bandwidth

1,008 GB/s

2,039 GB/s

Shared memory

-

-

Display Connectors

1x HDMI 2.1, 3x DisplayPort 1.4a

No outputs

HDMI

+

-

DirectX

12 Ultimate (12_2)

N/A

CUDA

8.9

9.0

OpenCL

3.0

3.0

OpenGL

4.6

N/A

Shader Model

6.6

N/A

Vulkan

1.3

N/A