NVIDIA B100 vs NVIDIA A16 PCIe
We compared two Desktop platform GPUs: 96GB VRAM B100 and 16GB VRAM A16 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA B100 's Advantages
Released 3 years and 7 months late
Boost Clock has increased by 8% (1837MHz vs 1695MHz)
More VRAM (96GB vs 16GB)
Larger VRAM bandwidth (4.10TB/s vs 231.9GB/s)
15616 additional rendering cores
NVIDIA A16 PCIe 's Advantages
Lower TDP (250W vs 1000W)
Score
Benchmark
FP32 (float)
B100
+1330%
62.08 TFLOPS
A16 PCIe
4.339 TFLOPS
Graphics Card
Nov 2024
Release Date
Apr 2021
Server Blackwell
Generation
Tesla
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x8
Clock Speeds
1665 MHz
Base Clock
885 MHz
1837 MHz
Boost Clock
1695 MHz
2000 MHz
Memory Clock
1812 MHz
Memory
96GB
Memory Size
16GB
HBM3e
Memory Type
GDDR6
4096bit
Memory Bus
128bit
4.10TB/s
Bandwidth
231.9GB/s
Render Config
-
-
-
132
SM Count
10
16896
Shading Units
1280
528
TMUs
40
24
ROPs
32
528
Tensor Cores
40
-
RT Cores
10
256 KB (per SM)
L1 Cache
128 KB (per SM)
50 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
44.09 GPixel/s
Pixel Rate
54.24 GPixel/s
969.9 GTexel/s
Texture Rate
67.80 GTexel/s
248.3 TFLOPS
FP16 (half)
4.339 TFLOPS
62.08 TFLOPS
FP32 (float)
4.339 TFLOPS
31.04 TFLOPS
FP64 (double)
135.6 GFLOPS
Board Design
1000W
TDP
250W
1400 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
-
Power Connectors
8-pin EPS
Graphics Processor
GB102
GPU Name
GA107
-
-
-
Blackwell
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
104 billion
Transistors
Unknown
Unknown
Die Size
Unknown
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
10.1
CUDA
8.6
N/A
Shader Model
6.6
