Cast your vote Do you agree or disagree with GPUBoss?

Thanks for adding your opinion. Follow us on Facebook to stay up to date with the latest news!
VS

Differences What are the advantages of each

Front view of GeForce GTX 660

Reasons to consider the
Nvidia GeForce GTX 660

Report a correction
Significantly higher clock speed 980 MHz vs 810 MHz More than 20% higher clock speed
Significantly higher effective memory clock speed 6,008 MHz vs 3,200 MHz Around 90% higher effective memory clock speed
More memory 2,048 MB vs 1,024 MB 2x more memory
Higher memory bandwidth 144.2 GB/s vs 51.2 GB/s More than 2.8x higher memory bandwidth
Better floating-point performance 1,882 GFLOPS vs 311 GFLOPS More than 6x better floating-point performance
Higher texture rate 78.4 GTexel/s vs 13 GTexel/s More than 6x higher texture rate
Higher pixel rate 19.6 GPixel/s vs 3.24 GPixel/s More than 6x higher pixel rate
Much higher memory clock speed 1,502 MHz vs 800 MHz Around 90% higher memory clock speed
More render output processors 24 vs 4 20 more render output processors
More shading units 960 vs 96 864 more shading units
More texture mapping units 80 vs 16 64 more texture mapping units
Wider memory bus 192 bit vs 128 bit 50% wider memory bus
Front view of GeForce GT 630

Reasons to consider the
EVGA GeForce GT 630

Report a correction
Lower TDP 65W vs 140W 2.2x lower TDP

Features Key features of the GeForce GTX 660  vs GT 630 

memory bandwidth Rate at which data can be read from or stored in onboard memory

GeForce GTX 660
144.2 GB/s
GeForce GT 630
51.2 GB/s
The 25% narrower memory-bus width shouldn't worry you because NVIDIA uses 6.00 GHz memory clock speed, resulting in a memory bandwidth of 144.
GeForce GTX 660 | by techPowerUp! (Sep, 2012)

pixel rate Number of pixels a graphics card can render to the screen every second

GeForce GTX 660
19.6 GPixel/s
GeForce GT 630
3.24 GPixel/s
In terms of performance, we see an 8% performance improvement compared to the reference GTX 660.
GeForce GTX 660 | by techPowerUp! (Oct, 2012)

texture rate Speed at which a graphics card can perform texture mapping

GeForce GTX 660
78.4 GTexel/s
GeForce GT 630
13 GTexel/s
We benchmarked using the highest settings possible in DirectX 11 mode, which was added via a patch after release.
GeForce GTX 660 | by techPowerUp! (Sep, 2012)

floating point performance How fast the gpu can crunch numbers

GeForce GTX 660
1,882 GFLOPS
GeForce GT 630
311 GFLOPS
It makes use of Bethesda's Creation Engine, which isn't visually intensive in that it doesn't use taxing graphics features.
GeForce GTX 660 | by techPowerUp! (Sep, 2012)

shading units Subcomponents of the gpu, these run in parallel to enable fast pixel shading

texture mapping units Built into each gpu, these resize and rotate bitmaps for texturing scenes

The GK106 silicon packs a total of 960 CUDA cores, with 80 texture memory units (TMUs), 24 raster operations processors (ROPs), and a 192-bit wide GDDR5 memory interface.
GeForce GTX 660 | by techPowerUp! (Sep, 2012)

Specifications Full list of technical specs

gpu

GeForce GTX 660  vs
GT 630 
GPU brand Nvidia Nvidia
GPU name GK106 GF108
Market Desktop Desktop
Clock speed 980 MHz 810 MHz
Is dual GPU No No
Reference card None Nvidia GeForce GT 630 810 MHz 1 GB

raw performance

Shading units 960 96
Texture mapping units 80 16
Render output processors 24 4
Pixel rate 19.6 GPixel/s 3.24 GPixel/s
Texture rate 78.4 GTexel/s 13 GTexel/s
Floating-point performance 1,882 GFLOPS 311 GFLOPS

memory

GeForce GTX 660  vs
GT 630 
Memory clock speed 1,502 MHz 800 MHz
Effective memory clock speed 6,008 MHz 3,200 MHz
Memory bus 192 bit 128 bit
Memory 2,048 MB 1,024 MB
Memory type GDDR5 GDDR5
Memory bandwidth 144.2 GB/s 51.2 GB/s

noise and power

TDP 140W 65W

Comments

comments powered by Disqus