GeForce GTX 680 vs L20
We compared two Desktop platform GPUs: 2GB VRAM GeForce GTX 680 and 48GB VRAM L20 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce GTX 680 's Advantages
Lower TDP (195W vs 275W)
L20 's Advantages
Released 11 years and 8 months late
Boost Clock has increased by 138% (2520MHz vs 1058MHz)
More VRAM (48GB vs 2GB)
Larger VRAM bandwidth (864.0GB/s vs 192.3GB/s)
10240 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 680
3250
L20
+1726%
59350
Graphics Card
Mar 2012
Release Date
Nov 2023
GeForce 600
Generation
Tesla Ada
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1006 MHz
Base Clock
1440 MHz
1058 MHz
Boost Clock
2520 MHz
1502 MHz
Memory Clock
2250 MHz
Memory
2GB
Memory Size
48GB
GDDR5
Memory Type
GDDR6
256bit
Memory Bus
384bit
192.3GB/s
Bandwidth
864.0GB/s
Render Config
-
SM Count
92
1536
Shading Units
11776
128
TMUs
368
32
ROPs
128
-
Tensor Cores
368
-
RT Cores
92
16 KB (per SMX)
L1 Cache
128 KB (per SM)
512 KB
L2 Cache
96 MB
Theoretical Performance
33.86 GPixel/s
Pixel Rate
322.6 GPixel/s
135.4 GTexel/s
Texture Rate
927.4 GTexel/s
-
FP16 (half)
59.35 TFLOPS
3.250 TFLOPS
FP32 (float)
59.35 TFLOPS
135.4 GFLOPS
FP64 (double)
927.4 GFLOPS
Board Design
195W
TDP
275W
450 W
Suggested PSU
600 W
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
Outputs
4x DisplayPort 1.4a
2x 6-pin
Power Connectors
1x 16-pin
Graphics Processor
GK104
GPU Name
AD102
GK104-400-A2
GPU Variant
AD102
Kepler
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
28 nm
Process Size
5 nm
3.54 billion
Transistors
76.3 billion
294 mm²
Die Size
609 mm²
Graphics Features
12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.0
CUDA
8.9
5.1
Shader Model
6.7
