GeForce GTX 470 vs Radeon HD 7670A

If you are going to buy a new graphics card and are choosing between GeForce GTX 470 and Radeon HD 7670A, 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 470 stacks up against Radeon HD 7670A, check out specs charts below.

Main Specs

  GeForce GTX 470 Radeon HD 7670A
Power consumption (TDP) 215 Watt 45 Watt
Interface PCIe 2.0 x16 MXM-A (3.0)
Supplementary power connectors Two 6-pins
Memory type GDDR5 GDDR5
Maximum RAM amount 1280 MB 1 GB
Display Connectors 2x DVI, 1x mini-HDMI No outputs
  Check Price
  • GeForce GTX 470 has 377% more power consumption, than Radeon HD 7670A.
  • GeForce GTX 470 is connected by PCIe 2.0 x16, and Radeon HD 7670A uses MXM-A (3.0) interface.
  • GeForce GTX 470 has 1279 GB more memory, than Radeon HD 7670A.
  • Both cards are used in Desktops.
  • GeForce GTX 470 is build with Fermi architecture, and Radeon HD 7670A - with TeraScale 2.
  • Core clock speed of GeForce GTX 470 is 615 MHz higher, than Radeon HD 7670A.
  • GeForce GTX 470 and Radeon HD 7670A are manufactured by 40 nm process technology.
  • Memory clock speed of Radeon HD 7670A is 2326 MHz higher, than GeForce GTX 470.

Game benchmarks

high / 1080p 16−18 1−2
ultra / 1080p 10−11 0−1
QHD / 1440p 4−5 0−1
4K / 2160p 4−5
low / 720p 30−35 12−14
medium / 1080p 21−24 3−4
The average gaming FPS of GeForce GTX 470 in Assassin's Creed Odyssey is 300% more, than Radeon HD 7670A.

Full Specs

  GeForce GTX 470 Radeon HD 7670A
Architecture Fermi TeraScale 2
Code name GF100 Turks
Type Desktop Desktop
Release date 12 April 2010 5 January 2012
Pipelines 448 480
Core clock speed 1215 MHz 600 MHz
Transistor count 3,100 million 716 million
Manufacturing process technology 40 nm 40 nm
Texture fill rate 34.0 billion/sec 14.40
Floating-point performance 1,088.6 gflops 576.0 gflops
Length 9.5" (241 mm) (24.1 cm)
Memory bus width 320 Bit 128 Bit
Memory clock speed 1674 MHz (3348 data rate) 4000 MHz
Memory bandwidth 133.9 GB/s 64 GB/s
Shared memory -
DirectX 12 (11_0) 11.2 (11_0)
Shader Model 5.1 5.0
OpenGL 4.2 4.4
OpenCL 1.1 1.2
Vulkan N/A N/A
CUDA +
CUDA cores 448
Bus support 16x PCI-E 2.0
Height 4.376" (111 mm) (11.1 cm)
SLI options +
Multi monitor support +
HDMI +
Maximum VGA resolution 2048x1536
Audio input for HDMI Internal
Bitcoin / BTC (SHA256) 97 Mh/s
  Check Price