NVIDIA H100 PCIe 80 GB vs NVIDIA GeForce GTX 1650 TU106
GPU · Specs Compare
Graphics Card
Release Date
Oct 2022
Jun 2020
Generation
Server Hopper
GeForce 16
Type
AI GPU
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1095 MHz
1410 MHz
Boost Clock
1755 MHz
1590 MHz
Memory Clock
1593 MHz
1500 MHz
Memory
Memory Size
80GB
4GB
Memory Type
HBM2e
GDDR6
Memory Bus
5120bit
128bit
Bandwidth
2.04TB/s
192.0GB/s
Render Config
SM Count
114
14
Shading Units
14592
896
TMUs
456
56
ROPs
24
32
Tensor Cores
456
—
L1 Cache
256 KB (per SM)
64 KB (per SM)
L2 Cache
50 MB
1024 KB
Theoretical Performance
Pixel Rate
42.12 GPixel/s
50.88 GPixel/s
Texture Rate
800.3 GTexel/s
89.04 GTexel/s
FP16 (half)
204.9 TFLOPS
5.699 TFLOPS
FP32 (float)
51.22 TFLOPS
2.849 TFLOPS
FP64 (double)
25.61 TFLOPS
89.04 GFLOPS
Graphics Processor
GPU Name
GH100
TU106
Architecture
Hopper
Turing
Foundry
TSMC
TSMC
Process Size
5 nm
12 nm
Transistors
80 billion
10.8 billion
Die Size
814 mm²
445 mm²
GPU Variant
—
TU106-125-KAB-A1
Board Design
TDP
350W
90W
Suggested PSU
750 W
250 W
Outputs
No outputs
1x DVI1x HDMI 2.01x DisplayPort 1.4a
Power Connectors
1x 16-pin
1x 6-pin
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
1.3
CUDA
9.0
7.5
Shader Model
N/A
6.6
▲ Specs Compare
Data sourced from official specifications and benchmark tests.