NVIDIA L40 CNX vs NVIDIA RTX PRO 4000 Blackwell

GPU Specs Compare

G

NVIDIA L40 CNX

NVIDIA 2022-10

Graphics Card

Release Date
Oct 2022
Mar 2025
Generation
Tesla Ada
Blackwell PRO W
Type
Professional
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16

Clock Speeds

Base Clock
1005 MHz
1230 MHz
Boost Clock
2475 MHz
2055 MHz
Memory Clock
2250 MHz
1750 MHz

Memory

Memory Size
24GB
24GB
Memory Type
GDDR6
GDDR7
Memory Bus
384bit
192bit
Bandwidth
864.0GB/s
672.0GB/s

Render Config

SM Count
142
70
Shading Units
18176
8960
TMUs
568
280
ROPs
192
96
Tensor Cores
568
280
RT Cores
142
70
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
48 MB
48 MB

Theoretical Performance

Pixel Rate
475.2 GPixel/s
197.3 GPixel/s
Texture Rate
1406 GTexel/s
575.4 GTexel/s
FP16 (half)
89.97 TFLOPS
36.83 TFLOPS
FP32 (float)
89.97 TFLOPS
36.83 TFLOPS
FP64 (double)
1406 GFLOPS
575.4 GFLOPS

Graphics Processor

GPU Name
AD102
GB203
GPU Variant
AD102-???-A1
-
Architecture
Ada Lovelace
Blackwell 2.0
Foundry
TSMC
TSMC
Process Size
4 nm
5 nm
Transistors
76.3 billion
45.6 billion
Die Size
608 mm²
378 mm²

Board Design

TDP
300W
140W
Suggested PSU
700 W
300 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
4x DisplayPort 2.1b
Power Connectors
1x 16-pin
1x 16-pin

Graphics Features

DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.4
CUDA
8.9
12.0
Shader Model
6.6
6.8