GeForce 8800 GTX vs Radeon HD 7670A

If you are going to buy a new graphics card and are choosing between GeForce 8800 GTX 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 8800 GTX stacks up against Radeon HD 7670A, check out specs charts below.
GeForce 8800 GTX
Radeon HD 7670A

Main Specs

  GeForce 8800 GTX Radeon HD 7670A
Power consumption (TDP) 155 Watt 45 Watt
Interface PCIe 1.0 x16 MXM-A (3.0)
Supplementary power connectors 2x 6-pin
Memory type GDDR3 GDDR5
Maximum RAM amount 768 MB 1 GB
Display Connectors 2x DVI, 1x S-Video No outputs
 
  • GeForce 8800 GTX has 244% more power consumption, than Radeon HD 7670A.
  • GeForce 8800 GTX is connected by PCIe 1.0 x16, and Radeon HD 7670A uses MXM-A (3.0) interface.
  • GeForce 8800 GTX has 767 GB more memory, than Radeon HD 7670A.
  • Both cards are used in Desktops.
  • GeForce 8800 GTX is build with Tesla architecture, and Radeon HD 7670A - with TeraScale 2.
  • Core clock speed of Radeon HD 7670A is 24 MHz higher, than GeForce 8800 GTX.
  • GeForce 8800 GTX is manufactured by 90 nm process technology, and Radeon HD 7670A - by 40 nm process technology.
  • Memory clock speed of Radeon HD 7670A is 3100 MHz higher, than GeForce 8800 GTX.

Game benchmarks

high / 1080p 0−1 1−2
ultra / 1080p 0−1
QHD / 1440p 0−1 0−1
low / 720p 1−2 12−14
medium / 1080p 0−1 3−4
The average gaming FPS of Radeon HD 7670A in Assassin's Creed Odyssey is 1200% more, than GeForce 8800 GTX.

Full Specs

  GeForce 8800 GTX Radeon HD 7670A
Architecture Tesla TeraScale 2
Code name G80 Turks
Type Desktop Desktop
Release date 8 November 2006 5 January 2012
Pipelines 128 480
Core clock speed 576 MHz 600 MHz
Transistor count 681 million 716 million
Manufacturing process technology 90 nm 40 nm
Texture fill rate 36.8 billion/sec 14.40
Floating-point performance 345.6 gflops 576.0 gflops
Length 270 mm
Memory bus width 384 Bit 128 Bit
Memory clock speed 900 MHz 4000 MHz
Memory bandwidth 86.4 GB/s 64 GB/s
DirectX 11.1 (10_0) 11.2 (11_0)
Shader Model 4.0 5.0
OpenGL 3.3 4.4
OpenCL 1.1 1.2
Vulkan N/A N/A
CUDA +
CUDA cores 575
SLI options +