NVIDIA Jetson Orin Nano Super vs NVIDIA H100 CNX
GPU · Specs Compare
Graphics Card
Release Date
Dec 2024
Mar 2023
Generation
Tegra
Tesla Hopper
Type
Mobile
AI GPU
Bus Interface
PCIe 4.0 x4
PCIe 5.0 x16
Clock Speeds
Memory Clock
800 MHz
1593 MHz
Base Clock
—
690 MHz
Boost Clock
—
1845 MHz
Memory
Memory Size
8GB
80GB
Memory Type
LPDDR5
HBM2e
Memory Bus
128bit
5120bit
Bandwidth
102.4GB/s
2039GB/s
Render Config
SM Count
8
114
Shading Units
1024
14592
TMUs
32
456
ROPs
16
24
Tensor Cores
32
456
L1 Cache
128 KB (per SM)
256 KB (per SM)
L2 Cache
2 MB
50 MB
Theoretical Performance
Pixel Rate
16.32 GPixel/s
44.28 GPixel/s
Texture Rate
32.64 GTexel/s
841.3 GTexel/s
FP16 (half)
4.178 TFLOPS
215.4 TFLOPS
FP32 (float)
2.089 TFLOPS
53.84 TFLOPS
FP64 (double)
—
26.92 TFLOPS
Graphics Processor
GPU Name
GA10B
GH100
Architecture
Ampere
Hopper
Foundry
Samsung
TSMC
Process Size
8 nm
4 nm
Transistors
Unknown
80 billion
Die Size
200 mm²
814 mm²
Board Design
TDP
25W
350W
Outputs
Portable Device Dependent
No outputs
Suggested PSU
—
750 W
Power Connectors
—
8-pin EPS
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.4
N/A
CUDA
8.7
9.0
Shader Model
6.8
N/A
▲ Specs Compare
Data sourced from official specifications and benchmark tests.