GeForce GT 730 vs GeForce GTX 960

GeForce GT 730
Memory: 1024Mb DDR3DESKTOP
Release date: 18 Jun 2014
GeForce GT 730
GeForce GTX 960
Memory: 2048Mb GDDR5DESKTOP
Release date: 22 Jan 2015
GeForce GTX 960

Summary

Reasons to consider GeForce GT 730

71 watts lower power draw. This might be a strong point if your current power supply is not enough to handle the GeForce GTX 960 .
Supports PhysX
Based on an outdated architecture (Nvidia Fermi), there are no performance optimizations for current games and applications

Reasons to consider GeForce GTX 960

Higher theoretical gaming performance, based on specifications.
Supports PhysX
Supports G-Sync
Supports ShadowPlay (allows game streaming/recording with minimum performance penalty)
Based on an outdated architecture (Nvidia Maxwell), there may be no performance optimizations for current games and applications

GeForce GTX 960

HWBench recommends GeForce GTX 960

Based on theoretical specifications.


Specifications

Core Configuration

GeForce GT 730GeForce GTX 960
GPU NameGF108 (GF108-400-A1)vsGM206 (GM206-300-A1)
Fab Process40 nmvs28 nm
Die Size116 mm²vs228 mm²
Transistors585 millionvs2,940 million
Shaders96vs1024
Compute Units2vs8
Core clock700 MHzvs1127 MHz
ROPs4vs32
TMUs16vs64

Memory Configuration

GeForce GT 730GeForce GTX 960
Memory TypeDDR3vsGDDR5
Bus Width128 bitvs128 bit
Memory Speed900 MHz
1800 MHz effective
vs1753 MHz
7012 MHz effective
Memory Size1024 Mbvs2048 Mb

Additional details

GeForce GT 730GeForce GTX 960
TDP49 wattsvs120 watts
Release Date18 Jun 2014vs22 Jan 2015

Raw Performance comparison

Pixel Rate

  • GeForce GT 730
    2.80 GP/s
  • GeForce GTX 960
    36.10 GP/s

GigaPixels - higher is better

Texel Rate

  • GeForce GT 730
    11.20 GT/s
  • GeForce GTX 960
    72.10 GT/s

GigaTexels - higher is better

Memory bandwidth

  • GeForce GT 730
    28.80 GB/s
  • GeForce GTX 960
    112.20 GB/s

GB/s - higher is better

Single precision performance

  • GeForce GT 730
    268.80 GFLOPs
  • GeForce GTX 960
    2308.10 GFLOPs

GFLOPs - higher is better