GeForce RTX 3070 Max-Q and RTX A40 - video card comparison
GeForce RTX 3070 Max-Q
RTX A40
Architecture
Ampere (2020−2022)
Ampere (2020−2022)
GPU code name
GN20-E5 GA104
GA102
Market segment
Laptop
Desktop
Release date
January 2021
October 2020
Interface
PCIe 4.0 x16
PCIe 4.0 x16
Supplementary power connectors
None
8-pin EPS
Boost clock speed
1290 MHz
1755 MHz
Manufacturing process technology
8 nm
8 nm
Number of transistors
17,400 million
28,300 million
Pipelines / CUDA cores
5120
10752
Power consumption (TDP)
80 Watt
300 Watt
Texture fill rate
237.4
589.7
Memory type
GDDR6
GDDR6
Maximum RAM amount
8 GB
48 GB
Memory bus width
256 Bit
384 Bit
Memory clock speed
12 GB/s
14.5 GB/s
Memory bandwidth
320.0 GB/s
695.8 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
3x DisplayPort
HDMI
+
-
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
CUDA
8.6
8.6
OpenCL
2.0
2.0
OpenGL
4.6
4.6
Shader Model
6.5
6.5
Vulkan
1.2
1.2