NVIDIA GRID RTX T10 4 vs NVIDIA Quadro P620
We compared two Professional market GPUs: 4GB VRAM GRID RTX T10 4 and 2GB VRAM Quadro P620 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID RTX T10 4 's Advantages
Released 1 years and 11 months late
Boost Clock has increased by 3% (1395MHz vs 1354MHz)
More VRAM (4GB vs 2GB)
Larger VRAM bandwidth (672.0GB/s vs 80.13GB/s)
3072 additional rendering cores
NVIDIA Quadro P620 's Advantages
Lower TDP (40W vs 150W)
Score
Benchmark
FP32 (float)
GRID RTX T10 4
+621%
9.999 TFLOPS
Quadro P620
1.386 TFLOPS
Graphics Card
Jan 2020
Release Date
Feb 2018
GRID
Generation
Quadro
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1065 MHz
Base Clock
1266 MHz
1395 MHz
Boost Clock
1354 MHz
1750 MHz
Memory Clock
1252 MHz
Memory
4GB
Memory Size
2GB
GDDR6
Memory Type
GDDR5
384bit
Memory Bus
128bit
672.0GB/s
Bandwidth
80.13GB/s
Render Config
-
-
-
56
SM Count
4
3584
Shading Units
512
224
TMUs
32
64
ROPs
16
448
Tensor Cores
-
56
RT Cores
-
64 KB (per SM)
L1 Cache
48 KB (per SM)
6 MB
L2 Cache
1024 KB
-
-
-
Theoretical Performance
89.28 GPixel/s
Pixel Rate
21.66 GPixel/s
312.5 GTexel/s
Texture Rate
43.33 GTexel/s
20.00 TFLOPS
FP16 (half)
21.66 GFLOPS
9.999 TFLOPS
FP32 (float)
1386 GFLOPS
312.5 GFLOPS
FP64 (double)
43.33 GFLOPS
Board Design
150W
TDP
40W
450 W
Suggested PSU
200 W
No outputs
Outputs
4x mini-DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
None
Graphics Processor
TU102
GPU Name
GP107
TU102-875-A1
GPU Variant
-
Turing
Architecture
Pascal
TSMC
Foundry
Samsung
12 nm
Process Size
14 nm
18.6 billion
Transistors
3.3 billion
754 mm²
Die Size
132 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.5
CUDA
6.1
6.8
Shader Model
6.4
