GeForce RTX 2050 vs GeForce GTX 960

GeForce RTX 2050
Memory: 4096Mb GDDR6DESKTOP
Release date: UNRELEASED
GeForce RTX 2050
GeForce GTX 960
Memory: 2048Mb GDDR5DESKTOP
Release date: 22 Jan 2015
GeForce GTX 960

Summary

Reasons to consider GeForce RTX 2050

Higher theoretical gaming performance, based on specifications.
Supports PhysX
Supports G-Sync
Supports ShadowPlay (allows game streaming/recording with minimum performance penalty)
Supports Direct3D 12 Async Compute
Supports DirectX Raytracing (DXR)
Supports Deep Learning Super-Sampling (DLSS)

Reasons to consider GeForce GTX 960

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Based on an outdated architecture (Nvidia Maxwell), there may be no performance optimizations for current games and applications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 RTX 2050

HWBench recommends GeForce RTX 2050

Based on theoretical specifications.


Specifications

Core Configuration

GeForce RTX 2050GeForce GTX 960
GPU NameTU107 (TU107)vsGM206 (GM206-300-A1)
Fab Process12 nmvs28 nm
Die Size0 mm²vs228 mm²
Transistorsunknownvs2,940 million
Shaders896vs1024
Compute Units14vs8
Core clock1515 MHzvs1127 MHz
ROPs32vs32
TMUs56vs64

Memory Configuration

GeForce RTX 2050GeForce GTX 960
Memory TypeGDDR6vsGDDR5
Bus Width128 bitvs128 bit
Memory Speed1750 MHz
14000 MHz effective
vs1753 MHz
7012 MHz effective
Memory Size4096 Mbvs2048 Mb

Additional details

GeForce RTX 2050GeForce GTX 960
TDP120 wattsvs120 watts
Release DateUNRELEASEDvs22 Jan 2015

Raw Performance comparison

Pixel Rate

  • GeForce RTX 2050
    54.24 GP/s
  • GeForce GTX 960
    36.10 GP/s

GigaPixels - higher is better

Texel Rate

  • GeForce RTX 2050
    94.92 GT/s
  • GeForce GTX 960
    72.10 GT/s

GigaTexels - higher is better

Memory bandwidth

  • GeForce RTX 2050
    224.00 GB/s
  • GeForce GTX 960
    112.20 GB/s

GB/s - higher is better

Single precision performance

  • GeForce RTX 2050
    3037.00 GFLOPs
  • GeForce GTX 960
    2308.10 GFLOPs

GFLOPs - higher is better