GeForce RTX 3080 Ti and H100 SXM5 - video card comparison
GeForce RTX 3080 Ti
H100 SXM5
Architecture
Ampere (2020−2022)
Hopper (2022)
GPU code name
Ampere GA102
GH100
Market segment
Desktop
Desktop
Release date
September 2020
March 2022
Interface
PCIe 4.0 x16
PCIe 5.0 x16
Supplementary power connectors
1x 12-pin
8-pin EPS
Boost clock speed
1667 MHz
1780 MHz
Core clock speed
1370 MHz
-
Manufacturing process technology
8 nm
4 nm
Number of transistors
28,300 million
80,000 million
Pipelines / CUDA cores
10240
8448
Power consumption (TDP)
350 Watt
700 Watt
Texture fill rate
532.8
939.8
Memory type
GDDR6X
HBM3
Maximum RAM amount
12 GB
80 GB
Memory bus width
384 Bit
5120 Bit
Memory clock speed
19000 MHz
3 GB/s
Memory bandwidth
912.4 GB/s
1,920 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
No outputs
HDMI
+
-
DirectX
12 Ultimate (12_2)
N/A
CUDA
8.6
9.0
OpenCL
3.0
3.0
OpenGL
4.6
N/A
Shader Model
6.6
N/A
Vulkan
1.2
N/A