GeForce GTX 1650 vs GeForce GT 630

GeForce GTX 1650
Memory: 4096Mb GDDR5 DESKTOP
Release date: 30 Apr 2019
GeForce GTX 1650
GeForce GT 630
Memory: 1024Mb DDR3 DESKTOP
Release date: 15 May 2012
GeForce GT 630

Summary

Reasons to consider GeForce GTX 1650

This is a much newer product, it might have better long term support.
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 GT 630

Supports PhysX.
Based on an outdated architecture (Nvidia Fermi), there are no performance optimizations for current games and applications.

GeForce GTX 1650

HWBench recommends GeForce GTX 1650

Based on theoretical specifications.


Specifications

Core Configuration

GeForce GTX 1650 GeForce GT 630
GPU Name TU107 () vs GF108 (GF108-400-A1)
Fab Process 12 nm vs 40 nm
Die Size 0 mm² vs 116 mm²
Transistors unknown vs 585 million
Shaders 896 vs 96
Compute Units 14 vs 2
Core clock 1485 MHz vs 810 MHz
ROPs 32 vs 4
TMUs 56 vs 16

Memory Configuration

GeForce GTX 1650 GeForce GT 630
Memory Type GDDR5 vs DDR3
Bus Width 128 bit vs 128 bit
Memory Speed 2000 MHz
8000 MHz effective
vs 900 MHz
1800 MHz effective
Memory Size 4096 Mb vs 1024 Mb

Additional details

GeForce GTX 1650 GeForce GT 630
TDP 0 watts vs 65 watts
Release Date 30 Apr 2019 vs 15 May 2012

Raw Performance comparison

Pixel Rate

  • GeForce GTX 1650
    53.28 GP/s
  • GeForce GT 630
    3.24 GP/s

GigaPixels - higher is better

Texel Rate

  • GeForce GTX 1650
    93.24 GT/s
  • GeForce GT 630
    13.00 GT/s

GigaTexels - higher is better

Memory bandwidth

  • GeForce GTX 1650
    128.00 GB/s
  • GeForce GT 630
    28.80 GB/s

GB/s - higher is better

Single precision performance

  • GeForce GTX 1650
    2984.00 GFLOPs
  • GeForce GT 630
    311.00 GFLOPs

GFLOPs - higher is better