NVIDIA Quadro K620 vs NVIDIA GRID A100B
We compared two Professional market GPUs: 2GB VRAM Quadro K620 and 48GB VRAM GRID A100B to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Quadro K620 's Advantages
Boost Clock has increased by 12% (1124MHz vs 1005MHz)
Lower TDP (45W vs 400W)
NVIDIA GRID A100B 's Advantages
Released 5 years and 10 months late
More VRAM (48GB vs 2GB)
Larger VRAM bandwidth (1866GB/s vs 28.80GB/s)
6528 additional rendering cores
Score
Benchmark
FP32 (float)
Quadro K620
0.863 TFLOPS
GRID A100B
+1509%
13.89 TFLOPS
Graphics Card
Jul 2014
Release Date
May 2020
Quadro
Generation
GRID
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1058 MHz
Base Clock
900 MHz
1124 MHz
Boost Clock
1005 MHz
900 MHz
Memory Clock
1215 MHz
Memory
2GB
Memory Size
48GB
DDR3
Memory Type
HBM2e
128bit
Memory Bus
6144bit
28.80GB/s
Bandwidth
1866GB/s
Render Config
-
-
-
-
SM Count
108
384
Shading Units
6912
24
TMUs
432
16
ROPs
192
-
Tensor Cores
432
-
-
-
64 KB (per SMM)
L1 Cache
192 KB (per SM)
2 MB
L2 Cache
48 MB
-
-
-
Theoretical Performance
17.98 GPixel/s
Pixel Rate
193.0 GPixel/s
26.98 GTexel/s
Texture Rate
434.2 GTexel/s
-
FP16 (half)
55.57 TFLOPS
863.2 GFLOPS
FP32 (float)
13.89 TFLOPS
26.98 GFLOPS
FP64 (double)
6.947 TFLOPS
Board Design
45W
TDP
400W
200 W
Suggested PSU
800 W
1x DVI
1x DisplayPort 1.4a
Outputs
No outputs
None
Power Connectors
None
Graphics Processor
GM107
GPU Name
GA100
GM107-850-A2
GPU Variant
-
Maxwell
Architecture
Ampere
TSMC
Foundry
TSMC
28 nm
Process Size
7 nm
1.87 billion
Transistors
54.2 billion
148 mm²
Die Size
826 mm²
Graphics Features
12 (11_0)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
5.0
CUDA
8.0
5.1
Shader Model
N/A
