
H100 PCIe 80 GB and GeForce RTX 5080 - video card comparison
H100 PCIe 80 GB
GeForce RTX 5080
Architecture
Hopper (2022)
Blackwell 2.0
GPU code name
GH100
GB203
Market segment
Desktop
Desktop
Release date
March 2023
2025 (recently)
Interface
PCIe 5.0 x16
PCIe 5.0 x16
Supplementary power connectors
1x 16-pin
1x 16-pin
Boost clock speed
1755 MHz
2520 MHz
Manufacturing process technology
4 nm
0 nm
Number of transistors
80,000 million
-
Pipelines / CUDA cores
14592
10752
Power consumption (TDP)
350 Watt
350 Watt
Texture fill rate
800.3
846.7
Memory type
HBM2e
GDDR7
Maximum RAM amount
80 GB
16 GB
Memory bus width
5120 Bit
256 Bit
Memory clock speed
3.2 GB/s
5 GB/s
Memory bandwidth
2,039 GB/s
160.0 GB/s
Display Connectors
No outputs
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
-
+
DirectX
N/A
12 Ultimate (12_2)
CUDA
9.0
9.1
OpenCL
3.0
3.0
OpenGL
N/A
4.6
Shader Model
N/A
6.7
Vulkan
N/A
1.3