Data Center GPU Flex 140 vs L40 CNX
We compared two Professional market GPUs: 6GB VRAM Data Center GPU Flex 140 and 24GB VRAM L40 CNX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Data Center GPU Flex 140 's Advantages
Lower TDP (75W vs 300W)
L40 CNX 's Advantages
Boost Clock has increased by 27% (2475MHz vs 1950MHz)
More VRAM (24GB vs 6GB)
Larger VRAM bandwidth (864.0GB/s vs 186.0GB/s)
17152 additional rendering cores
Score
Benchmark
FP32 (float)
Data Center GPU Flex 140
3994
L40 CNX
+2152%
89970
Graphics Card
Aug 2022
Release Date
Oct 2022
Data Center GPU
Generation
Tesla Ada
Professional
Type
Professional
PCIe 4.0 x8
Bus Interface
PCIe 4.0 x16
Clock Speeds
1600 MHz
Base Clock
1005 MHz
1950 MHz
Boost Clock
2475 MHz
1937 MHz
Memory Clock
2250 MHz
Memory
6GB
Memory Size
24GB
GDDR6
Memory Type
GDDR6
96bit
Memory Bus
384bit
186.0GB/s
Bandwidth
864.0GB/s
Render Config
-
SM Count
142
1024
Shading Units
18176
64
TMUs
568
32
ROPs
192
-
Tensor Cores
568
8
RT Cores
142
-
L1 Cache
128 KB (per SM)
4 MB
L2 Cache
48 MB
Theoretical Performance
62.40 GPixel/s
Pixel Rate
475.2 GPixel/s
124.8 GTexel/s
Texture Rate
1406 GTexel/s
7.987 TFLOPS
FP16 (half)
89.97 TFLOPS
3.994 TFLOPS
FP32 (float)
89.97 TFLOPS
-
FP64 (double)
1406 GFLOPS
Board Design
75W
TDP
300W
250 W
Suggested PSU
700 W
1x HDMI 2.1
3x DisplayPort 2.0
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
DG2-128
GPU Name
AD102
ACM-G11
GPU Variant
AD102-???-A1
Generation 12.7
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
6 nm
Process Size
4 nm
7.2 billion
Transistors
76.3 billion
157 mm²
Die Size
608 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
8.9
6.6
Shader Model
6.6
