NVIDIA L20 vs NVIDIA GeForce RTX 3060 Ti GDDR6X
We compared two Desktop platform GPUs: 48GB VRAM L20 and 8GB VRAM GeForce RTX 3060 Ti GDDR6X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L20 's Advantages
Released 1 years and 1 months late
Boost Clock has increased by 51% (2520MHz vs 1665MHz)
More VRAM (48GB vs 8GB)
Larger VRAM bandwidth (864.0GB/s vs 608.3GB/s)
6912 additional rendering cores
NVIDIA GeForce RTX 3060 Ti GDDR6X 's Advantages
Lower TDP (225W vs 275W)
Score
Benchmark
FP32 (float)
L20
+266%
59.35 TFLOPS
GeForce RTX 3060 Ti GDDR6X
16.2 TFLOPS
Graphics Card
Nov 2023
Release Date
Oct 2022
Tesla Ada
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1440 MHz
Base Clock
1410 MHz
2520 MHz
Boost Clock
1665 MHz
2250 MHz
Memory Clock
1188 MHz
Memory
48GB
Memory Size
8GB
GDDR6
Memory Type
GDDR6X
384bit
Memory Bus
256bit
864.0GB/s
Bandwidth
608.3GB/s
Render Config
-
-
-
92
SM Count
38
11776
Shading Units
4864
368
TMUs
152
128
ROPs
80
368
Tensor Cores
152
92
RT Cores
38
128 KB (per SM)
L1 Cache
128 KB (per SM)
96 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
322.6 GPixel/s
Pixel Rate
133.2 GPixel/s
927.4 GTexel/s
Texture Rate
253.1 GTexel/s
59.35 TFLOPS
FP16 (half)
16.20 TFLOPS
59.35 TFLOPS
FP32 (float)
16.20 TFLOPS
927.4 GFLOPS
FP64 (double)
253.1 GFLOPS
Board Design
275W
TDP
225W
600 W
Suggested PSU
550 W
4x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 12-pin
Graphics Processor
AD102
GPU Name
GA104
AD102
GPU Variant
GA104-202-A1
Ada Lovelace
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
76.3 billion
Transistors
17.4 billion
609 mm²
Die Size
392 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
8.6
6.7
Shader Model
6.7
