GeForce RTX 4090 and GeForce RTX 5070 - video card comparison
GeForce RTX 4090
GeForce RTX 5070
Architecture
Ada Lovelace
Blackwell 2.0
GPU code name
AD102-300-A1
GB205
Market segment
Desktop
Desktop
Release date
September 2022
2025 (recently)
Interface
PCIe 4.0 x16
PCIe 5.0 x16
Supplementary power connectors
1x 16-pin
1x 16-pin
Boost clock speed
2520 MHz
2520 MHz
Core clock speed
2235 MHz
-
Manufacturing process technology
5 nm
0 nm
Number of transistors
76,300 million
-
Pipelines / CUDA cores
16384
6400
Power consumption (TDP)
450 Watt
220 Watt
Texture fill rate
1,290
504.0
Memory type
GDDR6X
GDDR7
Maximum RAM amount
24 GB
12 GB
Memory bus width
384 Bit
192 Bit
Memory clock speed
21000 MHz
5 GB/s
Memory bandwidth
1,008 GB/s
120.0 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
9.1
OpenCL
3.0
3.0
OpenGL
4.6
4.6
Shader Model
6.6
6.7
Vulkan
1.3
1.3