3.3
Check Prices $179.00
2.6
Check Prices $499.00
Select any two GPUs for comparison
VS

Gaming Performance Comparison

Recommended System Requirements
Game Radeon RX 470 XFX Single Fan Triple X 4GB GeForce GTX 680
Cyberpunk 2077 25% 59%
Assassins Creed: Valhalla 15% 46%
Call of Duty: Black Ops Cold War 11% 41%
FIFA 21 37% 20%
Watch Dogs Legion 21% 54%
Microsoft Flight Simulator 11% 41%
World of Warcraft: Shadowlands 80% 128%
Grand Theft Auto VI 76% 124%
Godfall 103% 158%
Genshin Impact 25% 59%

In terms of overall gaming performance, the graphical capabilities of the AMD Radeon RX 470 XFX Single Fan Triple X 4GB are noticeably better than the Nvidia GeForce GTX 680.

The GeForce GTX 680 has a 80 MHz higher core clock speed and 32 more Texture Mapping Units than the RX 470. This results in the GeForce GTX 680 providing 39.9 GTexel/s better texturing performance. This still holds weight but shader performance is generally more relevant, particularly since both of these GPUs support at least DirectX 10.

The GeForce GTX 680 has a 80 MHz higher core clock speed than the RX 470, but the RX 470 has 16 more Render Output Units than the GeForce GTX 680. As a result, the RX 470 exhibits a 12.2 GPixel/s better Pixel Fill Rate than the GeForce GTX 680. However, both GPUs support DirectX 9 or above, and pixeling performance is only really relevant when comparing older cards.

The RX 470 was released over three years more recently than the GeForce GTX 680, and so the RX 470 is likely to have far better driver support, meaning it will be much more optimized and ultimately superior to the GeForce GTX 680 when running the latest games.

Both GPUs exhibit very powerful performance, so it probably isn't worth upgrading from one to the other, as both are capable of running even the most demanding games at the highest settings.

The RX 470 has 2048 MB more video memory than the GeForce GTX 680, so is likely to be much better at displaying game textures at higher resolutions. This is supported by the fact that the RX 470 also has superior memory performance overall.

The RX 470 has 18.9 GB/sec greater memory bandwidth than the GeForce GTX 680, which means that the memory performance of the RX 470 is slightly better than the GeForce GTX 680.

The Radeon RX 470 XFX Single Fan Triple X 4GB has 2048 Shader Processing Units and the GeForce GTX 680 has 1536. However, the actual shader performance of the RX 470 is 2511 and the actual shader performance of the GeForce GTX 680 is 1625. The RX 470 having 886 better shader performance and an altogether better performance when taking into account other relevant data means that the RX 470 delivers a noticeably smoother and more efficient experience when processing graphical data than the GeForce GTX 680.

The RX 470 transistor size technology is 14 nm (nanometers) smaller than the GeForce GTX 680. This means that the RX 470 is expected to run slightly cooler and achieve higher clock frequencies than the GeForce GTX 680.

The Radeon RX 470 XFX Single Fan Triple X 4GB requires 120 Watts to run and the GeForce GTX 680 requires 195 Watts. We would recommend a PSU with at least 450 Watts for the RX 470 and a PSU with at least 550 Watts for the GeForce GTX 680. The GeForce GTX 680 requires 75 Watts more than the RX 470 to run. The difference is significant enough that the GeForce GTX 680 may have an adverse affect on your yearly electricity bills in comparison to the RX 470.

Game FPS Benchmarks On Ultra

GPU Architecture

Core Speed926 MHzvs1006 MHz
Boost Clock1226 MHzvs1058 MHz
ArchitectureGCN 1.3 Ellesmere PROKepler GK104-400-A2
OC Potential None vs Good
Driver Support Great vs Good
Release Date04 Aug 2016vs22 Mar 2012
GPU LinkGD LinkGD Link
Approved
Comparison

Resolution Performance

1366x768
10
green tick vs green tick
10
1600x900
10
green tick vs green tick
10
1920x1080
9.4
green tick vs
8.4
2560x1440
7
green tick vs
6.1
3840x2160
5.3
green tick vs
4.5

GPU Memory

Memory4096 MBvs2048 MB
Memory Speed1650 MHzvs1502 MHz
Memory Bus256 Bitvs256 Bit
Memory TypeGDDR5vsGDDR5
Memory Bandwidth211.2GB/secvs192.3GB/sec
L2 Cache 2048 KB green tick vs 512 KB
Delta Color Compression yes vs no
Memory Performance 0% green tick vs green tick 0%
Comparison

GPU Display

Shader Processing Units2048vs1536
Actual Shader Performance100%vs78%
Technology14nmvs28nm
Texture Mapping Units96vs128
Texture Rate88.9 GTexel/svs128.8 GTexel/s
Render Output Units48vs32
Pixel Rate44.4 GPixel/svs32.2 GPixel/s
Comparison

GPU Outputs

Max Digital Resolution (WxH)4096x2160vs4096x2160
VGA Connections0vs0
DVI Connections1vs2
HDMI Connections1vs1
DisplayPort Connections3vs-
Comparison

GPU Power Requirements

Max Power120 Wattsvs195 Watts
Recommended PSU450 Watts & 30 Ampsvs550 Watts & 40 Amps

GPU Features

DirectX12.0vs12.0
Shader Model5.0vs5.0
Open GL4.5vs4.5
Open CL-vs-
Notebook GPUnono
SLI/Crossfireyesvsyes
Dedicatedyesvsyes
Comparison

GPU Supporting Hardware

Recommended ProcessorIntel Core i5-6600K 3.5GHzvsIntel Core i7-3770K 4-Core 3.5GHz
Recommended RAM8 GBvs8 GB
Maximum Recommended Gaming Resolution1920x1080vs1920x1080

Gaming Performance Value

Performance Value

GPU Mini Review

Mini ReviewOverview
Radeon RX 470 4GB XFX Triple X is single fan small form factor performance graphics card, based on the fourth revision of the Graphics Core Next (GCN) Architecture.

Architecture
N/A.

GPU
It equips a GPU Codenamed Ellesmere PRO which has 24 SM activated and thus 2048 Shader Processing Units, 128 TMUs and 32 ROPs.

Memory
The GPU accesses a 8GB frame buffer of Fast GDDR5, through a 256-bit memory interface, while the Memory Clock Operates at 1750MHz.

Power Consumption
With a rated board TDP of 120W, it requires at least a 450W PSU with one available 6-pin connector.

Performance
The RX 470 should run most modern AAA games at 1080p on high graphics settings.

System Suggestions
Radeon RX 470 4GB is best suited for resolutions up to and including 1920x1080. We recommend a Performance Processor and 8GB of RAM for Optimal Performance.
GeForce GTX 680 is a high-end Graphics Card based on the 28nm, Kepler architecture.
The Kepler architecture allows more SPUs but the Fermi SPUs (used on the 400 & 500 Series) are clocked twice as fast as the Kepler architecture. Therefore, don't let the large amount of Pipelines fool you, as the 1536 Pipelines are equivalent to 768 Pipelines, of the Fermi architecture.
GeForce GTX 680 features a 1006Mhz core-clock that can automatically set itself to 1058Mhz using a technology similar to the one used on Intel GPUs. Another huge surprise is the TDP that went from 244 Watts, to just 195 Watts, as two SPUs of the Kepler architecture consume 10% less power. However, the amount was doubled and so the power save is not as high as it could have been.
GeForce GTX 680 was the fastest single GPU of the world until Radeon HD 7970 GHz Edition was released.
All games will run on the maximum settings smoothly.
Recommended CPU
Possible GPU Upgrades
-
-
GPU Variants
-