GeForce GTX 660 vs Radeon Pro 580X

If you are going to buy a new graphics card and are choosing between GeForce GTX 660 and Radeon Pro 580X, 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 660 stacks up against Radeon Pro 580X, check out specs charts below.

Main Specs

  GeForce GTX 660 Radeon Pro 580X
Power consumption (TDP) 140 Watt 150 Watt
Interface PCIe 3.0 x16 PCIe 3.0 x16
Supplementary power connectors One 6-pin None
Memory type GDDR5 GDDR5
Maximum RAM amount 2 GB 8 GB
Display Connectors 2x DVI, 1x HDMI, 1x DisplayPort No outputs
  Check Price
  • Radeon Pro 580X has 7% more power consumption, than GeForce GTX 660.
  • Both video cards are using PCIe 3.0 x16 interface connection to a motherboard.
  • Radeon Pro 580X has 6 GB more memory, than GeForce GTX 660.
  • Both cards are used in Desktops.
  • GeForce GTX 660 is build with Kepler architecture, and Radeon Pro 580X - with GCN 4.0.
  • Core clock speed of Radeon Pro 580X is 120 MHz higher, than GeForce GTX 660.
  • GeForce GTX 660 is manufactured by 28 nm process technology, and Radeon Pro 580X - by 14 nm process technology.
  • Memory clock speed of Radeon Pro 580X is 6774 MHz higher, than GeForce GTX 660.

Game benchmarks

high / 1080p 20−22 35−40
ultra / 1080p 12−14 24−27
QHD / 1440p 6−7 18−20
4K / 2160p 5−6 10−12
low / 720p 40−45 60−65
medium / 1080p 24−27 45−50
The average gaming FPS of Radeon Pro 580X in Assassin's Creed Odyssey is 73% more, than GeForce GTX 660.

Full Specs

  GeForce GTX 660 Radeon Pro 580X
Architecture Kepler GCN 4.0
Code name GK106 Polaris 20
Type Desktop Workstation
Release date 6 September 2012 18 March 2019
Pipelines 960 2304
Core clock speed 980 MHz 1100 MHz
Boost Clock 1033 MHz 1200 MHz
Transistor count 2,540 million 5,700 million
Manufacturing process technology 28 nm 14 nm
Texture fill rate 78.4 billion/sec 172.8
Floating-point performance 1,981 gflops
Length 9.5" (24.1 cm)
Memory bus width 192-bit GDDR5 256 Bit
Memory clock speed 6.0 GB/s 6780 MHz
Memory bandwidth 144.2 GB/s 217.0 GB/s
DirectX 12 (11_0) 12 (12_0)
Shader Model 5.1 6.4
OpenGL 4.3 4.6
OpenCL 1.2 2.0
Vulkan 1.1.126 1.2.131
CUDA +
CUDA cores 960
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
3D Blu-Ray +
3D Gaming +
3D Vision +
Bitcoin / BTC (SHA256) 66 Mh/s
  Check Price