L4 vs Quadro P620
We compared two Professional market GPUs: 24GB VRAM L4 and 2GB VRAM Quadro P620 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
L4 's Advantages
Released 5 years and 1 months late
Boost Clock has increased by 51% (2040MHz vs 1354MHz)
More VRAM (24GB vs 2GB)
Larger VRAM bandwidth (300.1GB/s vs 80.13GB/s)
6912 additional rendering cores
Quadro P620 's Advantages
Lower TDP (40W vs 72W)
Score
Benchmark
FP32 (float)
L4
+2085%
30290
Quadro P620
1386
Graphics Card
Mar 2023
Release Date
Feb 2018
Tesla Ada(Lxx)
Generation
Quadro
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
795 MHz
Base Clock
1266 MHz
2040 MHz
Boost Clock
1354 MHz
1563 MHz
Memory Clock
1252 MHz
Memory
24GB
Memory Size
2GB
GDDR6
Memory Type
GDDR5
192bit
Memory Bus
128bit
300.1GB/s
Bandwidth
80.13GB/s
Render Config
60
SM Count
4
7424
Shading Units
512
240
TMUs
32
80
ROPs
16
240
Tensor Cores
-
60
RT Cores
-
128 KB (per SM)
L1 Cache
48 KB (per SM)
48 MB
L2 Cache
1024 KB
Theoretical Performance
163.2 GPixel/s
Pixel Rate
21.66 GPixel/s
489.6 GTexel/s
Texture Rate
43.33 GTexel/s
30.29 TFLOPS
FP16 (half)
21.66 GFLOPS
30.29 TFLOPS
FP32 (float)
1386 GFLOPS
473.3 GFLOPS
FP64 (double)
43.33 GFLOPS
Board Design
72W
TDP
40W
250 W
Suggested PSU
200 W
No outputs
Outputs
4x mini-DisplayPort 1.4a
None
Power Connectors
None
Graphics Processor
AD104
GPU Name
GP107
AD104-???-A1
GPU Variant
-
Ada Lovelace
Architecture
Pascal
TSMC
Foundry
Samsung
5 nm
Process Size
14 nm
35.8 billion
Transistors
3.3 billion
294 mm²
Die Size
132 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.9
CUDA
6.1
6.8
Shader Model
6.4
