NVIDIA GRID A100B vs NVIDIA Quadro FX 3700
We compared two Professional market GPUs: 48GB VRAM GRID A100B and 512MB VRAM Quadro FX 3700 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID A100B 's Advantages
Released 12 years and 4 months late
Boost Clock1005MHz
More VRAM (48GB vs 512GB)
Larger VRAM bandwidth (1866GB/s vs 51.20GB/s)
6800 additional rendering cores
NVIDIA Quadro FX 3700 's Advantages
Lower TDP (78W vs 400W)
Score
Benchmark
FP32 (float)
GRID A100B
+4860%
13.89 TFLOPS
Quadro FX 3700
0.28 TFLOPS
Graphics Card
May 2020
Release Date
Jan 2008
GRID
Generation
Quadro FX
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
900 MHz
Base Clock
-
1005 MHz
Boost Clock
-
1215 MHz
Memory Clock
800 MHz
Memory
48GB
Memory Size
512MB
HBM2e
Memory Type
GDDR3
6144bit
Memory Bus
256bit
1866GB/s
Bandwidth
51.20GB/s
Render Config
-
-
-
108
SM Count
14
6912
Shading Units
112
432
TMUs
56
192
ROPs
16
432
Tensor Cores
-
-
-
-
192 KB (per SM)
L1 Cache
-
48 MB
L2 Cache
64 KB
-
-
-
Theoretical Performance
193.0 GPixel/s
Pixel Rate
8.000 GPixel/s
434.2 GTexel/s
Texture Rate
28.00 GTexel/s
55.57 TFLOPS
FP16 (half)
-
13.89 TFLOPS
FP32 (float)
280.0 GFLOPS
6.947 TFLOPS
FP64 (double)
-
Board Design
400W
TDP
78W
800 W
Suggested PSU
250 W
No outputs
Outputs
2x DVI
1x S-Video
None
Power Connectors
1x 6-pin
Graphics Processor
GA100
GPU Name
G92
-
GPU Variant
G92-875-A2
Ampere
Architecture
Tesla
TSMC
Foundry
TSMC
7 nm
Process Size
65 nm
54.2 billion
Transistors
0.754 billion
826 mm²
Die Size
324 mm²
Graphics Features
N/A
DirectX
11.1 (10_0)
N/A
OpenGL
3.3
3.0
OpenCL
1.1
N/A
Vulkan
N/A
8.0
CUDA
1.1
N/A
Shader Model
4.0
