GeForce RTX 3070 and RTX A40 - video card comparison
GeForce RTX 3070
RTX A40
Architecture
Ampere (2020−2022)
Ampere (2020−2022)
GPU code name
Ampere GA104
GA102
Market segment
Desktop
Desktop
Release date
September 2020
October 2020
Interface
PCIe 4.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 12-pin
8-pin EPS
Boost clock speed
1725 MHz
1755 MHz
Core clock speed
1500 MHz
-
Manufacturing process technology
8 nm
8 nm
Number of transistors
17,400 million
28,300 million
Pipelines / CUDA cores
5888
10752
Power consumption (TDP)
220 Watt
300 Watt
Texture fill rate
317.4
589.7
Memory type
GDDR6
GDDR6
Maximum RAM amount
8 GB
48 GB
Memory bus width
256 Bit
384 Bit
Memory clock speed
14000 MHz
14.5 GB/s
Memory bandwidth
448.0 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
8.5
8.6
OpenCL
2.0
2.0
OpenGL
4.6
4.6
Shader Model
6.5
6.5
Vulkan
1.2
1.2