Radeon RX 470 and GeForce RTX 4080 Ti - video card comparison
Radeon RX 470
GeForce RTX 4080 Ti
Architecture
Polaris (2016−2019)
Ada Lovelace
GPU code name
Polaris 10 Pro
AD102
Market segment
Desktop
Desktop
Release date
August 2016
2023
Interface
PCIe 3.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 6-pin
1x 16-pin
Boost clock speed
1206 MHz
2610 MHz
Core clock speed
926 MHz
-
Floating-point performance
4,940 gflops
-
Manufacturing process technology
14 nm
5 nm
Number of transistors
5,700 million
76,300 million
Pipelines / CUDA cores
2048
14080
Power consumption (TDP)
120 Watt
400 Watt
Texture fill rate
154.4
1,148
Memory type
GDDR5
GDDR6X
Maximum RAM amount
8 GB
16 GB
Memory bus width
256 Bit
256 Bit
Memory clock speed
6600 MHz
21.2 GB/s
Memory bandwidth
211.2 GB/s
678.4 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
+
+
DirectX
12 (12_0)
12 Ultimate (12_2)
CUDA
-
8.9
OpenCL
2.0
3.0
OpenGL
4.6
4.6
Shader Model
6.4
6.7
Vulkan
1.2.131
1.3
FreeSync
+
-