NVIDIA H100 PCIe 80 GB vs NVIDIA GeForce RTX 3080 Ti 20 GB
GPU Specs Compare
Graphics Card
Release Date
Oct 2022
Jun 2025
Generation
Server Hopper
Navi IV
Type
AI GPU
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1095 MHz
1700 MHz
Boost Clock
1755 MHz
3130 MHz
Memory Clock
1593 MHz
2518 MHz
Memory
Memory Size
80GB
8GB
Memory Type
HBM2e
GDDR6
Memory Bus
5120bit
128bit
Bandwidth
2.04TB/s
322.3GB/s
Render Config
SM Count
114
80
Shading Units
14592
2048
TMUs
456
128
ROPs
24
64
Tensor Cores
456
320
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
50 MB
4 MB
Compute Units
-
32
RT Cores
-
32
L3 Cache
-
32 MB
Theoretical Performance
Pixel Rate
42.12 GPixel/s
200.3 GPixel/s
Texture Rate
800.3 GTexel/s
400.6 GTexel/s
FP16 (half)
204.9 TFLOPS
51.28 TFLOPS
FP32 (float)
51.22 TFLOPS
25.64 TFLOPS
FP64 (double)
25.61 TFLOPS
801.3 GFLOPS
Graphics Processor
GPU Name
GH100
Navi 44
Architecture
Hopper
RDNA 4.0
Foundry
TSMC
TSMC
Process Size
5 nm
4 nm
Transistors
80 billion
29.7 billion
Die Size
814 mm²
199 mm²
GPU Variant
-
Navi 44 XT(215-176400102)
Board Design
TDP
350W
150W
Suggested PSU
750 W
450 W
Outputs
No outputs
1x HDMI 2.1b2x DisplayPort 2.1a
Power Connectors
1x 16-pin
1x 8-pin
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
2.2
Vulkan
N/A
1.3
CUDA
9.0
8.6
Shader Model
N/A
6.8
📊 Benchmark
Blender
-
5,956