Data Center GPU Max Subsystem and GeForce RTX 5080 - video card comparison
Data Center GPU Max Subsystem
GeForce RTX 5080
Architecture
Generation 12.5 (2021−2022)
Blackwell 2.0
GPU code name
Ponte Vecchio
GB203
Market segment
Desktop
Desktop
Release date
January 2023
2025 (recently)
Interface
PCIe 5.0 x16
PCIe 5.0 x16
Supplementary power connectors
1x 16-pin
1x 16-pin
Boost clock speed
1600 MHz
2520 MHz
Manufacturing process technology
10 nm
0 nm
Number of transistors
100,000 million
-
Pipelines / CUDA cores
16384
10752
Power consumption (TDP)
2400 Watt
350 Watt
Texture fill rate
1,638
846.7
Memory type
HBM2e
GDDR7
Maximum RAM amount
128 GB
16 GB
Memory bus width
8192 Bit
256 Bit
Memory clock speed
3.1 GB/s
5 GB/s
Memory bandwidth
3,205 GB/s
160.0 GB/s
Display Connectors
No outputs
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
-
+
DirectX
12 (12_1)
12 Ultimate (12_2)
CUDA
-
9.1
OpenCL
3.0
3.0
OpenGL
4.6
4.6
Shader Model
6.6
6.7
Vulkan
N/A
1.3