GeForce RTX 4070 and GeForce RTX 3060 3840SP - video card comparison
GeForce RTX 4070
GeForce RTX 3060 3840SP
Architecture
Ada Lovelace
Ampere (2020−2022)
GPU code name
AD104
GA106
Market segment
Desktop
Desktop
Release date
April 2023
2021
Interface
PCIe 4.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 16-pin
1x 12-pin
Boost clock speed
2475 MHz
1852 MHz
Core clock speed
1920 MHz
-
Manufacturing process technology
5 nm
8 nm
Number of transistors
35,800 million
12,000 million
Pipelines / CUDA cores
5888
3840
Power consumption (TDP)
200 Watt
185 Watt
Texture fill rate
455.4
222.2
Memory type
GDDR6X
GDDR6
Maximum RAM amount
12 GB
6 GB
Memory bus width
192 Bit
192 Bit
Memory clock speed
21000 MHz
14 GB/s
Memory bandwidth
504.2 GB/s
336.0 GB/s
Shared memory
-
-
Display Connectors
1x HDMI 2.1, 3x DisplayPort 1.4a
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
+
+
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
CUDA
8.9
8.6
OpenCL
3.0
3.0
OpenGL
4.6
4.6
Shader Model
6.7
6.7
Vulkan
1.3
1.3