NVIDIA RTX PRO 5000 Blackwell Embedded vs NVIDIA H100 PCIe 80 GB
GPU · Specs Compare
Graphics Card
Release Date
Unknown
Oct 2022
Generation
Blackwell-MW
Server Hopper
Type
Mobile
AI GPU
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1095 MHz
1095 MHz
Boost Clock
1740 MHz
1755 MHz
Memory Clock
1750 MHz
1593 MHz
Memory
Memory Size
24GB
80GB
Memory Type
GDDR7
HBM2e
Memory Bus
256bit
5120bit
Bandwidth
896.0GB/s
2.04TB/s
Render Config
SM Count
82
114
Shading Units
10496
14592
TMUs
328
456
ROPs
112
24
Tensor Cores
328
456
RT Cores
82
—
L1 Cache
128 KB (per SM)
256 KB (per SM)
L2 Cache
64 MB
50 MB
Theoretical Performance
Pixel Rate
194.9 GPixel/s
42.12 GPixel/s
Texture Rate
570.7 GTexel/s
800.3 GTexel/s
FP16 (half)
36.53 TFLOPS
204.9 TFLOPS
FP32 (float)
36.53 TFLOPS
51.22 TFLOPS
FP64 (double)
570.7 GFLOPS
25.61 TFLOPS
Graphics Processor
GPU Name
GB203
GH100
Architecture
Blackwell 2.0
Hopper
Foundry
TSMC
TSMC
Process Size
5 nm
5 nm
Transistors
45.6 billion
80 billion
Die Size
378 mm²
814 mm²
Board Design
TDP
95W
350W
Outputs
Portable Device Dependent
No outputs
Power Connectors
None
1x 16-pin
Suggested PSU
—
750 W
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
12.0
9.0
Shader Model
6.8
N/A
▲ Specs Compare
Data sourced from official specifications and benchmark tests.