GeForce GTX 660 vs Radeon HD 6870

Find out if it is worth upgrading your current GPU setup by comparing GeForce GTX 660 and Radeon HD 6870. Here you can take a closer look at graphics cards specs, such as core clock speed, memory type and size, display connectors, etc. The price, overall benchmark and gaming performances are usually defining factors when it comes to choosing between GeForce GTX 660 and Radeon HD 6870. Make sure that the graphics card has compatible dimensions and will properly fit in your new or current computer case. Also these graphics cards may have different system power recommendations, so take that into consideration and upgrade your PSU if necessary.

Main Specs

  GeForce GTX 660 Radeon HD 6870
Power consumption (TDP) 140 Watt 151 Watt
Interface PCIe 3.0 x16 PCIe 2.0 x16
Supplementary power connectors One 6-pin 2x 6-pin
Memory type GDDR5 GDDR5
Maximum RAM amount 2 GB 1 GB
Display Connectors 2x DVI, 1x HDMI, 1x DisplayPort 2x DVI, 1x HDMI, 2x mini-DisplayPort
  Check Price Check Price
  • Radeon HD 6870 has 7% more power consumption, than GeForce GTX 660.
  • GeForce GTX 660 is connected by PCIe 3.0 x16, and Radeon HD 6870 uses PCIe 2.0 x16 interface.
  • GeForce GTX 660 has 1 GB more memory, than Radeon HD 6870.
  • Both cards are used in Desktops.
  • GeForce GTX 660 is build with Kepler architecture, and Radeon HD 6870 - with Terascale 2.
  • GeForce GTX 660 is manufactured by 28 nm process technology, and Radeon HD 6870 - by 40 nm process technology.
  • Radeon HD 6870 is 211 mm longer, than GeForce GTX 660.
  • Memory clock speed of Radeon HD 6870 is 1044 MHz higher, than GeForce GTX 660.

Game benchmarks

high / 1080p 20−22 10−12
ultra / 1080p 12−14 6−7
QHD / 1440p 6−7 1−2
4K / 2160p 5−6
low / 720p 40−45 24−27
medium / 1080p 24−27 12−14
The average gaming FPS of GeForce GTX 660 in Assassin's Creed Odyssey is 90% more, than Radeon HD 6870.

Full Specs

  GeForce GTX 660 Radeon HD 6870
Architecture Kepler Terascale 2
Code name GK106 RV940 Barts
Type Desktop Desktop
Release date 6 September 2012 22 October 2010
Pipelines 960 1120
Core clock speed 980 MHz
Boost Clock 1033 MHz 900 MHz
Transistor count 2,540 million 1,700 million
Manufacturing process technology 28 nm 40 nm
Texture fill rate 78.4 billion/sec 50.40
Floating-point performance 1,981 gflops 2,016.0 gflops
Length 9.5" (24.1 cm) 220 mm
Memory bus width 192-bit GDDR5 256 Bit
Memory clock speed 6.0 GB/s 1050 MHz
Memory bandwidth 144.2 GB/s 134.4 GB/s
Shared memory -
DirectX 12 (11_0)
Shader Model 5.1 5.0
OpenGL 4.3 4.4
OpenCL 1.2 1.2
Vulkan 1.1.126
CUDA +
CUDA cores 960
Bus support PCI Express 3.0 PCIe 2.0 x16
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 213 Mh/s
Eyefinity +
Design reference
CrossFire +
  Check Price Check Price