GeForce GT 640 and GeForce RTX 4090 Max-Q - video card comparison
GeForce GT 640
GeForce RTX 4090 Max-Q
Architecture
Kepler (2012−2018)
Ada Lovelace
GPU code name
GK107
AD103
Market segment
Desktop
Desktop
Release date
June 2012
January 2023
Interface
PCIe 3.0 x16
PCIe 4.0 x16
Supplementary power connectors
None
None
Boost clock speed
-
1455 MHz
Core clock speed
902 MHz
-
Floating-point performance
692.7 gflops
-
Manufacturing process technology
28 nm
4 nm
Number of transistors
1,270 million
45,900 million
Pipelines / CUDA cores
384
9728
Power consumption (TDP)
65 Watt
80 Watt
Texture fill rate
28.86
442.3
Memory type
DDR3
GDDR6
Maximum RAM amount
2 GB
16 GB
Memory bus width
128 Bit
256 Bit
Memory clock speed
1782 MHz
14 GB/s
Memory bandwidth
28.51 GB/s
448.0 GB/s
Display Connectors
1x DVI, 1x HDMI, 1x DisplayPort
Portable Device Dependent
HDMI
+
-
DirectX
12 (11_0)
12 Ultimate (12_2)
CUDA
3.0
8.9
OpenCL
1.2
3.0
OpenGL
4.6
4.6
Shader Model
5.1
6.7
Vulkan
1.1.126
1.3