Data Center GPU Max Subsystem and GeForce RTX 4070 SUPER - video card comparison
Data Center GPU Max Subsystem
GeForce RTX 4070 SUPER
Architecture
Generation 12.5 (2021−2022)
Ada Lovelace
GPU code name
Ponte Vecchio
AD104
Market segment
Desktop
Desktop
Release date
January 2023
January 2024
Interface
PCIe 5.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 16-pin
1x 16-pin
Boost clock speed
1600 MHz
2475 MHz
Core clock speed
-
1980 MHz
Manufacturing process technology
10 nm
5 nm
Number of transistors
100,000 million
35,800 million
Pipelines / CUDA cores
16384
7168
Power consumption (TDP)
2400 Watt
220 Watt
Texture fill rate
1,638
584.6
Memory type
HBM2e
GDDR6X
Maximum RAM amount
128 GB
12 GB
Memory bus width
8192 Bit
192 Bit
Memory clock speed
3.1 GB/s
21000 MHz
Memory bandwidth
3,205 GB/s
504.2 GB/s
Shared memory
-
-
Display Connectors
No outputs
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
-
+
DirectX
12 (12_1)
12 Ultimate (12_2)
CUDA
-
8.9
OpenCL
3.0
3.0
OpenGL
4.6
4.6
Shader Model
6.6
6.7
Vulkan
N/A
1.3