NVIDIA Quadro K620M vs NVIDIA GRID RTX T10 4
We compared two Professional market GPUs: 2GB VRAM Quadro K620M and 4GB VRAM GRID RTX T10 4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Quadro K620M 's Advantages
Lower TDP (30W vs 150W)
NVIDIA GRID RTX T10 4 's Advantages
Released 4 years and 10 months late
Boost Clock has increased by 24% (1395MHz vs 1124MHz)
More VRAM (4GB vs 2GB)
Larger VRAM bandwidth (672.0GB/s vs 14.40GB/s)
3200 additional rendering cores
Score
Benchmark
FP32 (float)
Quadro K620M
0.863 TFLOPS
GRID RTX T10 4
+1058%
9.999 TFLOPS
Graphics Card
Mar 2015
Release Date
Jan 2020
Quadro Mobile
Generation
GRID
Professional
Type
Professional
MXM-A (3.0)
Bus Interface
PCIe 3.0 x16
Clock Speeds
1029 MHz
Base Clock
1065 MHz
1124 MHz
Boost Clock
1395 MHz
900 MHz
Memory Clock
1750 MHz
Memory
2GB
Memory Size
4GB
DDR3
Memory Type
GDDR6
64bit
Memory Bus
384bit
14.40GB/s
Bandwidth
672.0GB/s
Render Config
-
-
-
-
SM Count
56
384
Shading Units
3584
16
TMUs
224
8
ROPs
64
-
Tensor Cores
448
-
RT Cores
56
64 KB (per SMM)
L1 Cache
64 KB (per SM)
1024 KB
L2 Cache
6 MB
-
-
-
Theoretical Performance
8.992 GPixel/s
Pixel Rate
89.28 GPixel/s
17.98 GTexel/s
Texture Rate
312.5 GTexel/s
-
FP16 (half)
20.00 TFLOPS
863.2 GFLOPS
FP32 (float)
9.999 TFLOPS
26.98 GFLOPS
FP64 (double)
312.5 GFLOPS
Board Design
30W
TDP
150W
-
Suggested PSU
450 W
No outputs
Outputs
No outputs
None
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
GM108
GPU Name
TU102
N15M-Q3
GPU Variant
TU102-875-A1
Maxwell
Architecture
Turing
TSMC
Foundry
TSMC
28 nm
Process Size
12 nm
Unknown
Transistors
18.6 billion
Unknown
Die Size
754 mm²
Graphics Features
12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
5.0
CUDA
7.5
5.1
Shader Model
6.8
