Data Center GPU Max Subsystem vs Quadro NVS 420
We compared two Professional market GPUs: 128GB VRAM Data Center GPU Max Subsystem and 256MB VRAM Quadro NVS 420 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Data Center GPU Max Subsystem 's Advantages
Released 14 years late
Boost Clock1600MHz
More VRAM (128GB vs 256GB)
Larger VRAM bandwidth (3205GB/s vs 11.20GB/s)
16376 additional rendering cores
Quadro NVS 420 's Advantages
Lower TDP (40W vs 2400W)
Score
Benchmark
FP32 (float)
Data Center GPU Max Subsystem
+238218%
52430
Quadro NVS 420
22
Graphics Card
Jan 2023
Release Date
Jan 2009
Data Center GPU
Generation
Quadro NVS
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
900 MHz
Base Clock
-
1600 MHz
Boost Clock
-
1565 MHz
Memory Clock
700 MHz
Memory
128GB
Memory Size
256MB
HBM2e
Memory Type
GDDR3
8192bit
Memory Bus
64bit
3205GB/s
Bandwidth
11.20GB/s
Render Config
-
SM Count
1
16384
Shading Units
8
1024
TMUs
4
0
ROPs
4
1024
Tensor Cores
-
128
RT Cores
-
64 KB (per EU)
L1 Cache
-
408 MB
L2 Cache
16 KB
Theoretical Performance
0 MPixel/s
Pixel Rate
2.200 GPixel/s
1638 GTexel/s
Texture Rate
2.200 GTexel/s
52.43 TFLOPS
FP16 (half)
-
52.43 TFLOPS
FP32 (float)
22.40 GFLOPS
52.43 TFLOPS
FP64 (double)
-
Board Design
2400W
TDP
40W
2800 W
Suggested PSU
200 W
No outputs
Outputs
1x VHDCI
1x 16-pin
Power Connectors
None
Graphics Processor
Ponte Vecchio
GPU Name
G98
Generation 12.5
Architecture
Tesla
Intel
Foundry
TSMC
10 nm
Process Size
65 nm
100 billion
Transistors
0.21 billion
1280 mm²
Die Size
86 mm²
Graphics Features
12 (12_1)
DirectX
11.1 (10_0)
4.6
OpenGL
3.3
3.0
OpenCL
1.1
N/A
Vulkan
N/A
-
CUDA
1.1
6.6
Shader Model
4.0
