GeForce RTX 3080 12 GB vs GeForce GTX 660 OEM
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 3080 12 GB and 1536MB VRAM GeForce GTX 660 OEM to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3080 12 GB Advantages
Released 9 years and 5 months late
Boost Clock has increased by 93% (1710MHz vs 888MHz)
More VRAM (12GB vs 1536GB)
Larger VRAM bandwidth (912.4GB/s vs 134.4GB/s)
7808 additional rendering cores
GeForce GTX 660 OEM Advantages
Lower TDP (130W vs 350W)
Score
Benchmark
FP32 (float)
GeForce RTX 3080 12 GB
+1397%
30640
GeForce GTX 660 OEM
2046
3DMark Time Spy
GeForce RTX 3080 12 GB
+1461%
18647
GeForce GTX 660 OEM
1194
3DMark Time Spy Extreme
GeForce RTX 3080 12 GB
+3519%
9411
GeForce GTX 660 OEM
260
Graphics Card
Jan 2022
Release Date
Aug 2012
GeForce 30
Generation
GeForce 600
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1260 MHz
Base Clock
823 MHz
1710 MHz
Boost Clock
888 MHz
1188 MHz
Memory Clock
1400 MHz
Memory
12GB
Memory Size
1536MB
GDDR6X
Memory Type
GDDR5
384bit
Memory Bus
192bit
912.4GB/s
Bandwidth
134.4GB/s
Render Config
70
SM Count
-
8960
Shading Units
1152
280
TMUs
96
96
ROPs
24
280
Tensor Cores
-
70
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per SMX)
6 MB
L2 Cache
384 KB
Theoretical Performance
164.2 GPixel/s
Pixel Rate
21.31 GPixel/s
478.8 GTexel/s
Texture Rate
85.25 GTexel/s
30.64 TFLOPS
FP16 (half)
-
30.64 TFLOPS
FP32 (float)
2.046 TFLOPS
478.8 GFLOPS
FP64 (double)
85.25 GFLOPS
Board Design
350W
TDP
130W
750 W
Suggested PSU
300 W
1x HDMI 2.1
3x DisplayPort 1.4a
3x DisplayPort 1.4a
Outputs
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
1x HDMI 1.4a
1x DisplayPort 1.2
1x 12-pin
Power Connectors
1x 6-pin
Graphics Processor
GA102
GPU Name
GK104
GA102-220-A1
GPU Variant
GK104-200-KD-A2
Ampere
Architecture
Kepler
Samsung
Foundry
TSMC
8 nm
Process Size
28 nm
28.3 billion
Transistors
3.54 billion
628 mm²
Die Size
294 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.1
8.6
CUDA
3.0
6.8
Shader Model
5.1
