Intel Data Center GPU Max Subsystem vs NVIDIA Quadro K620M
We compared two Professional market GPUs: 128GB VRAM Data Center GPU Max Subsystem and 2GB VRAM Quadro K620M to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Data Center GPU Max Subsystem 's Advantages
Released 7 years and 10 months late
Boost Clock has increased by 42% (1600MHz vs 1124MHz)
More VRAM (128GB vs 2GB)
Larger VRAM bandwidth (3205GB/s vs 14.40GB/s)
16000 additional rendering cores
NVIDIA Quadro K620M 's Advantages
Lower TDP (30W vs 2400W)
Score
Benchmark
FP32 (float)
Data Center GPU Max Subsystem
+5975%
52.43 TFLOPS
Quadro K620M
0.863 TFLOPS
Graphics Card
Jan 2023
Release Date
Mar 2015
Data Center GPU
Generation
Quadro Mobile
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
MXM-A (3.0)
Clock Speeds
900 MHz
Base Clock
1029 MHz
1600 MHz
Boost Clock
1124 MHz
1565 MHz
Memory Clock
900 MHz
Memory
128GB
Memory Size
2GB
HBM2e
Memory Type
DDR3
8192bit
Memory Bus
64bit
3205GB/s
Bandwidth
14.40GB/s
Render Config
-
-
-
-
-
-
16384
Shading Units
384
1024
TMUs
16
0
ROPs
8
1024
Tensor Cores
-
128
RT Cores
-
64 KB (per EU)
L1 Cache
64 KB (per SMM)
408 MB
L2 Cache
1024 KB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
8.992 GPixel/s
1638 GTexel/s
Texture Rate
17.98 GTexel/s
52.43 TFLOPS
FP16 (half)
-
52.43 TFLOPS
FP32 (float)
863.2 GFLOPS
52.43 TFLOPS
FP64 (double)
26.98 GFLOPS
Board Design
2400W
TDP
30W
2800 W
Suggested PSU
-
No outputs
Outputs
No outputs
1x 16-pin
Power Connectors
None
Graphics Processor
Ponte Vecchio
GPU Name
GM108
-
GPU Variant
N15M-Q3
Generation 12.5
Architecture
Maxwell
Intel
Foundry
TSMC
10 nm
Process Size
28 nm
100 billion
Transistors
Unknown
1280 mm²
Die Size
Unknown
Graphics Features
12 (12_1)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
5.0
6.6
Shader Model
5.1
