NVIDIA L20 vs NVIDIA RTX 3500 Embedded Ada Generation
We compared two Desktop platform GPUs: 48GB VRAM L20 and 12GB VRAM RTX 3500 Embedded Ada Generation to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L20 's Advantages
Released 8 months late
Boost Clock has increased by 12% (2520MHz vs 2250MHz)
More VRAM (48GB vs 12GB)
Larger VRAM bandwidth (864.0GB/s vs 432.0GB/s)
6656 additional rendering cores
NVIDIA RTX 3500 Embedded Ada Generation 's Advantages
Lower TDP (100W vs 275W)
Score
Benchmark
FP32 (float)
L20
+157%
59.35 TFLOPS
RTX 3500 Embedded Ada Generation
23.04 TFLOPS
Graphics Card
Nov 2023
Release Date
Mar 2023
Tesla Ada
Generation
Quadro Ada-M
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1440 MHz
Base Clock
1725 MHz
2520 MHz
Boost Clock
2250 MHz
2250 MHz
Memory Clock
2250 MHz
Memory
48GB
Memory Size
12GB
GDDR6
Memory Type
GDDR6
384bit
Memory Bus
192bit
864.0GB/s
Bandwidth
432.0GB/s
Render Config
-
-
-
92
SM Count
40
11776
Shading Units
5120
368
TMUs
160
128
ROPs
64
368
Tensor Cores
160
92
RT Cores
40
128 KB (per SM)
L1 Cache
128 KB (per SM)
96 MB
L2 Cache
48 MB
-
-
-
Theoretical Performance
322.6 GPixel/s
Pixel Rate
144.0 GPixel/s
927.4 GTexel/s
Texture Rate
360.0 GTexel/s
59.35 TFLOPS
FP16 (half)
23.04 TFLOPS
59.35 TFLOPS
FP32 (float)
23.04 TFLOPS
927.4 GFLOPS
FP64 (double)
360.0 GFLOPS
Board Design
275W
TDP
100W
600 W
Suggested PSU
300 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
None
Graphics Processor
AD102
GPU Name
AD104
AD102
GPU Variant
-
Ada Lovelace
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
76.3 billion
Transistors
35.8 billion
609 mm²
Die Size
294 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
8.9
CUDA
8.9
6.7
Shader Model
6.7
