NVIDIA GeForce GTX 1070 GDDR5X vs NVIDIA L20
We compared two Desktop platform GPUs: 8GB VRAM GeForce GTX 1070 GDDR5X and 48GB VRAM L20 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce GTX 1070 GDDR5X 's Advantages
Lower TDP (150W vs 275W)
NVIDIA L20 's Advantages
Released 4 years and 11 months late
Boost Clock has increased by 50% (2520MHz vs 1683MHz)
More VRAM (48GB vs 8GB)
Larger VRAM bandwidth (864.0GB/s vs 256.3GB/s)
9856 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 1070 GDDR5X
6.463 TFLOPS
L20
+818%
59.35 TFLOPS
Graphics Card
Dec 2018
Release Date
Nov 2023
GeForce 10
Generation
Tesla Ada
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1506 MHz
Base Clock
1440 MHz
1683 MHz
Boost Clock
2520 MHz
1001 MHz
Memory Clock
2250 MHz
Memory
8GB
Memory Size
48GB
GDDR5X
Memory Type
GDDR6
256bit
Memory Bus
384bit
256.3GB/s
Bandwidth
864.0GB/s
Render Config
-
-
-
15
SM Count
92
1920
Shading Units
11776
120
TMUs
368
64
ROPs
128
-
Tensor Cores
368
-
RT Cores
92
48 KB (per SM)
L1 Cache
128 KB (per SM)
2 MB
L2 Cache
96 MB
-
-
-
Theoretical Performance
107.7 GPixel/s
Pixel Rate
322.6 GPixel/s
202.0 GTexel/s
Texture Rate
927.4 GTexel/s
101.0 GFLOPS
FP16 (half)
59.35 TFLOPS
6.463 TFLOPS
FP32 (float)
59.35 TFLOPS
202.0 GFLOPS
FP64 (double)
927.4 GFLOPS
Board Design
150W
TDP
275W
450 W
Suggested PSU
600 W
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
Outputs
4x DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
GP104
GPU Name
AD102
GP104-200-A1
GPU Variant
AD102
Pascal
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
16 nm
Process Size
5 nm
7.2 billion
Transistors
76.3 billion
314 mm²
Die Size
609 mm²
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
6.1
CUDA
8.9
6.4
Shader Model
6.7
