GeForce GTX 680 vs Radeon RX Vega 9

If you are going to buy a new graphics card and are choosing between GeForce GTX 680 and Radeon RX Vega 9, there are a couple of things to consider. Cards with more VRAM in general perform better and allow you to play on higher graphics settings. Size also makes a difference. A model with a large heatsink can occupy up to three expansion slots on a motherboard. Be sure you have enough room in your PC case. When comparing GPUs with different architectures, more processing cores and even higher TFLOPS will not always translate to better performance. To help you decide which GPU you need, we have measured frame rates in a number of popular games. For more on how the GeForce GTX 680 stacks up against Radeon RX Vega 9, check out specs charts below.

Radeon RX Vega 9 is a Laptop Graphics Card

Note: Radeon RX Vega 9 is only used in laptop graphics. It has lower GPU clock speed compared to the desktop variant, which results in lower power consumption, but also 10-30% lower gaming performance. Check available laptop models with Radeon RX Vega 9 here:

Main Specs

  GeForce GTX 680 Radeon RX Vega 9
Power consumption (TDP) 195 Watt
Interface PCIe 3.0 x16
Supplementary power connectors Two 6-pin
Memory type GDDR5
Maximum RAM amount 2048 MB
Display Connectors 2x DVI, 1x HDMI, 1x DisplayPort
  Check Price Check Price
  • GeForce GTX 680 is used in Desktops, and Radeon RX Vega 9 - in Laptops.
  • GeForce GTX 680 is build with Kepler architecture, and Radeon RX Vega 9 - with Vega.
  • GeForce GTX 680 is manufactured by 28 nm process technology, and Radeon RX Vega 9 - by 14 nm process technology.

Game benchmarks

high / 1080p 35−40 12−14
ultra / 1080p 21−24 8−9
QHD / 1440p 16−18 2−3
4K / 2160p 10−11
low / 720p 60−65 27−30
medium / 1080p 40−45 16−18
The average gaming FPS of GeForce GTX 680 in Assassin's Creed Odyssey is 176% more, than Radeon RX Vega 9.

Full Specs

  GeForce GTX 680 Radeon RX Vega 9
Architecture Kepler Vega
Code name GK104 Vega Raven Ridge
Type Desktop Laptop
Release date 22 March 2012 26 October 2017
Pipelines 1536 576
Core clock speed 1006 MHz
Boost Clock 1058 MHz 1300 MHz
Transistor count 3,540 million
Manufacturing process technology 28 nm 14 nm
Texture fill rate 128.8 billion/sec
Floating-point performance 3,090.4 gflops
Length 10.0" (25.4 cm)
Memory bus width 256-bit GDDR5
Memory clock speed 6000 MHz
Memory bandwidth 192.2 GB/s
Shared memory - -
DirectX 12 (11_0) DirectX 12_1
Shader Model 5.1
OpenGL 4.2
OpenCL 1.2
Vulkan 1.1.126
CUDA +
CUDA cores 1536
Bus support PCI Express 3.0
Height 4.376" (11.1 cm)
SLI options +
Multi monitor support 4 displays
HDMI +
HDCP +
Maximum VGA resolution 2048x1536
Audio input for HDMI Internal
Bitcoin / BTC (SHA256) 121 Mh/s
Ethereum / ETH (DaggerHashimoto) 15 Mh/s
  Check Price Check Price