GeForce RTX 3070 SUPER and GeForce RTX 4090 - video card comparison
GeForce RTX 3070 SUPER
GeForce RTX 4090
Architecture
Ampere (2020−2022)
Ada Lovelace
GPU code name
GA104
AD102-300-A1
Market segment
Desktop
Desktop
Release date
-
September 2022
Interface
PCIe 4.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 12-pin
1x 16-pin
Boost clock speed
1695 MHz
2520 MHz
Core clock speed
-
2235 MHz
Manufacturing process technology
8 nm
5 nm
Number of transistors
18,000 million
76,300 million
Pipelines / CUDA cores
6144
16384
Power consumption (TDP)
250 Watt
450 Watt
Texture fill rate
325.4
1,290
Memory type
GDDR6
GDDR6X
Maximum RAM amount
16 GB
24 GB
Memory bus width
256 Bit
384 Bit
Memory clock speed
16000 MHz
21000 MHz
Memory bandwidth
512.0 GB/s
1,008 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
+
+
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
CUDA
-
8.9
OpenCL
-
3.0
OpenGL
4.6
4.6
Shader Model
-
6.6
Vulkan
-
1.3