H100 CNX and GeForce RTX 4070 Ti SUPER - video card comparison
H100 CNX
GeForce RTX 4070 Ti SUPER
Architecture
Hopper (2022)
Ada Lovelace
GPU code name
GH100
AD103-275
Market segment
Desktop
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
2610 MHz
Core clock speed
-
2340 MHz
Manufacturing process technology
4 nm
5 nm
Number of transistors
80,000 million
45,900 million
Pipelines / CUDA cores
14592
8448
Power consumption (TDP)
350 Watt
285 Watt
Texture fill rate
841.3
689.0
Memory type
HBM2e
GDDR6X
Maximum RAM amount
80 GB
16 GB
Memory bus width
5120 Bit
256 Bit
Memory clock speed
3.2 GB/s
21000 MHz
Memory bandwidth
2,039 GB/s
716.8 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
3.0
OpenGL
N/A
4.6
Shader Model
N/A
6.7
Vulkan
N/A
1.3