NVIDIA P102 101 vs NVIDIA H200 NVL
We compared two Desktop platform GPUs: 10GB VRAM P102 101 and 141GB VRAM H200 NVL to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA P102 101 's Advantages
Lower TDP (250W vs 600W)
NVIDIA H200 NVL 's Advantages
Released 6 years and 10 months late
Boost Clock has increased by 7% (1785MHz vs 1670MHz)
More VRAM (141GB vs 10GB)
Larger VRAM bandwidth (4.89TB/s vs 320.3GB/s)
13696 additional rendering cores
Score
Benchmark
FP32 (float)
P102 101
10.69 TFLOPS
H200 NVL
+464%
60.32 TFLOPS
Graphics Card
Jan 2018
Release Date
Nov 2024
Mining GPUs
Generation
Server Hopper
Desktop
Type
Desktop
PCIe 3.0 x4
Bus Interface
PCIe 5.0 x16
Clock Speeds
1557 MHz
Base Clock
1365 MHz
1670 MHz
Boost Clock
1785 MHz
2002 MHz
Memory Clock
1593 MHz
Memory
10GB
Memory Size
141GB
GDDR5
Memory Type
HBM3e
320bit
Memory Bus
6144bit
320.3GB/s
Bandwidth
4.89TB/s
Render Config
-
-
-
25
SM Count
132
3200
Shading Units
16896
200
TMUs
528
80
ROPs
24
-
Tensor Cores
528
-
-
-
48 KB (per SM)
L1 Cache
256 KB (per SM)
0 MB
L2 Cache
50 MB
-
-
-
Theoretical Performance
133.6 GPixel/s
Pixel Rate
42.84 GPixel/s
334.0 GTexel/s
Texture Rate
942.5 GTexel/s
167.0 GFLOPS
FP16 (half)
241.3 TFLOPS
10.69 TFLOPS
FP32 (float)
60.32 TFLOPS
334.0 GFLOPS
FP64 (double)
30.16 TFLOPS
Board Design
250W
TDP
600W
600 W
Suggested PSU
1000 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
GP102
GPU Name
GH100
GP102-101-A1
GPU Variant
-
Pascal
Architecture
Hopper
TSMC
Foundry
TSMC
16 nm
Process Size
5 nm
11.8 billion
Transistors
80 billion
471 mm²
Die Size
814 mm²
Graphics Features
12 (12_1)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
6.1
CUDA
9.0
6.4
Shader Model
N/A
