GeForce RTX 4090 and L40 CNX - video card comparison
GeForce RTX 4090
L40 CNX
Architecture
Ada Lovelace
Ada Lovelace
GPU code name
AD102-300-A1
AD102
Market segment
Desktop
Desktop
Release date
September 2022
October 2022
Interface
PCIe 4.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 16-pin
1x 16-pin
Boost clock speed
2520 MHz
2475 MHz
Core clock speed
2235 MHz
-
Manufacturing process technology
5 nm
4 nm
Number of transistors
76,300 million
76,300 million
Pipelines / CUDA cores
16384
18176
Power consumption (TDP)
450 Watt
300 Watt
Texture fill rate
1,290
1,406
Memory type
GDDR6X
GDDR6
Maximum RAM amount
24 GB
24 GB
Memory bus width
384 Bit
384 Bit
Memory clock speed
21000 MHz
18 GB/s
Memory bandwidth
1,008 GB/s
864.0 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
8.9
OpenCL
3.0
3.0
OpenGL
4.6
4.6
Shader Model
6.6
6.7
Vulkan
1.3
1.3