NVIDIA B100 vs NVIDIA P102 100
We compared two Desktop platform GPUs: 96GB VRAM B100 and 5GB VRAM P102 100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA B100 's Advantages
Released 6 years and 9 months late
Boost Clock has increased by 9% (1837MHz vs 1683MHz)
More VRAM (96GB vs 5GB)
Larger VRAM bandwidth (4.10TB/s vs 440.3GB/s)
13696 additional rendering cores
NVIDIA P102 100 's Advantages
Lower TDP (250W vs 1000W)
Score
Benchmark
FP32 (float)
B100
+476%
62.08 TFLOPS
P102 100
10.77 TFLOPS
Graphics Card
Nov 2024
Release Date
Feb 2018
Server Blackwell
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x4
Clock Speeds
1665 MHz
Base Clock
1582 MHz
1837 MHz
Boost Clock
1683 MHz
2000 MHz
Memory Clock
1376 MHz
Memory
96GB
Memory Size
5GB
HBM3e
Memory Type
GDDR5X
4096bit
Memory Bus
320bit
4.10TB/s
Bandwidth
440.3GB/s
Render Config
-
-
-
132
SM Count
25
16896
Shading Units
3200
528
TMUs
200
24
ROPs
80
528
Tensor Cores
-
-
-
-
256 KB (per SM)
L1 Cache
48 KB (per SM)
50 MB
L2 Cache
0 MB
-
-
-
Theoretical Performance
44.09 GPixel/s
Pixel Rate
134.6 GPixel/s
969.9 GTexel/s
Texture Rate
336.6 GTexel/s
248.3 TFLOPS
FP16 (half)
168.3 GFLOPS
62.08 TFLOPS
FP32 (float)
10.77 TFLOPS
31.04 TFLOPS
FP64 (double)
336.6 GFLOPS
Board Design
1000W
TDP
250W
1400 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
-
Power Connectors
2x 8-pin
Graphics Processor
GB102
GPU Name
GP102
-
GPU Variant
GP102-100-A1
Blackwell
Architecture
Pascal
TSMC
Foundry
TSMC
5 nm
Process Size
16 nm
104 billion
Transistors
11.8 billion
Unknown
Die Size
471 mm²
Graphics Features
N/A
DirectX
12 (12_1)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
10.1
CUDA
6.1
N/A
Shader Model
6.4
