NVIDIA H100 PCIe vs NVIDIA GRID RTX T10 16
GPU · Specs Compare
Graphics Card
Release Date
Mar 2022
Unknown
Generation
Tesla Hopper
GRID
Type
AI GPU
Professional
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1095 MHz
1065 MHz
Boost Clock
1755 MHz
1395 MHz
Memory Clock
1593 MHz
1575 MHz
Memory
Memory Size
80GB
16GB
Memory Type
HBM2e
GDDR6
Memory Bus
5120bit
384bit
Bandwidth
2039GB/s
604.8GB/s
Render Config
SM Count
114
56
Shading Units
14592
3584
TMUs
456
224
ROPs
24
64
Tensor Cores
456
448
L1 Cache
256 KB (per SM)
64 KB (per SM)
L2 Cache
50 MB
6 MB
RT Cores
—
56
Theoretical Performance
Pixel Rate
42.12 GPixel/s
89.28 GPixel/s
Texture Rate
800.3 GTexel/s
312.5 GTexel/s
FP16 (half)
204.9 TFLOPS
20.00 TFLOPS
FP32 (float)
51.22 TFLOPS
9.999 TFLOPS
FP64 (double)
25.61 TFLOPS
312.5 GFLOPS
Graphics Processor
GPU Name
GH100
TU102
Architecture
Hopper
Turing
Foundry
TSMC
TSMC
Process Size
4 nm
12 nm
Transistors
80 billion
18.6 billion
Die Size
814 mm²
754 mm²
GPU Variant
—
TU102-875-A1
Board Design
TDP
350W
150W
Suggested PSU
750 W
450 W
Outputs
No outputs
No outputs
Power Connectors
1x 16-pin
1x 6-pin + 1x 8-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
6.8
▲ Specs Compare
Data sourced from official specifications and benchmark tests.