NVIDIA GeForce GTX 660 OEM vs NVIDIA GeForce RTX 5080 SUPER
We compared two Desktop platform GPUs: 1536MB VRAM GeForce GTX 660 OEM and 24GB VRAM GeForce RTX 5080 SUPER to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce GTX 660 OEM 's Advantages
Lower TDP (130W vs 360W)
NVIDIA GeForce RTX 5080 SUPER 's Advantages
Boost Clock has increased by 195% (2617MHz vs 888MHz)
More VRAM (24GB vs 1536GB)
Larger VRAM bandwidth (1.02TB/s vs 134.4GB/s)
9600 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 660 OEM
2.046 TFLOPS
GeForce RTX 5080 SUPER
+2650%
56.28 TFLOPS
Graphics Card
Aug 2012
Release Date
Unknown
GeForce 600
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
823 MHz
Base Clock
2295 MHz
888 MHz
Boost Clock
2617 MHz
1400 MHz
Memory Clock
2000 MHz
Memory
1536MB
Memory Size
24GB
GDDR5
Memory Type
GDDR7
192bit
Memory Bus
256bit
134.4GB/s
Bandwidth
1.02TB/s
Render Config
-
-
-
-
SM Count
84
1152
Shading Units
10752
96
TMUs
336
24
ROPs
112
-
Tensor Cores
336
-
RT Cores
84
16 KB (per SMX)
L1 Cache
128 KB (per SM)
384 KB
L2 Cache
64 MB
-
-
-
Theoretical Performance
21.31 GPixel/s
Pixel Rate
293.1 GPixel/s
85.25 GTexel/s
Texture Rate
879.3 GTexel/s
-
FP16 (half)
56.28 TFLOPS
2.046 TFLOPS
FP32 (float)
56.28 TFLOPS
85.25 GFLOPS
FP64 (double)
879.3 GFLOPS
Board Design
130W
TDP
360W
300 W
Suggested PSU
750 W
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1b
1x 6-pin
Power Connectors
1x 16-pin
Graphics Processor
GK104
GPU Name
GB203
GK104-200-KD-A2
GPU Variant
GB203-450-A1
Kepler
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
28 nm
Process Size
5 nm
3.54 billion
Transistors
45.6 billion
294 mm²
Die Size
378 mm²
Graphics Features
12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.4
3.0
CUDA
12.0
5.1
Shader Model
6.8
