GeForce 8800 GTX vs Radeon HD 4890

Find out if it is worth upgrading your current GPU setup by comparing GeForce 8800 GTX and Radeon HD 4890. 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 8800 GTX and Radeon HD 4890. 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 8800 GTX Radeon HD 4890
Power consumption (TDP) 155 Watt 190 Watt
Interface PCIe 1.0 x16 PCIe 2.0 x16
Supplementary power connectors 2x 6-pin 2x 6-pin
Memory type GDDR3 GDDR5
Maximum RAM amount 768 MB 1 GB
Display Connectors 2x DVI, 1x S-Video 2x DVI, 1x S-Video
  Check Price
  • Radeon HD 4890 has 22% more power consumption, than GeForce 8800 GTX.
  • GeForce 8800 GTX is connected by PCIe 1.0 x16, and Radeon HD 4890 uses PCIe 2.0 x16 interface.
  • GeForce 8800 GTX has 767 GB more memory, than Radeon HD 4890.
  • Both cards are used in Desktops.
  • GeForce 8800 GTX is build with Tesla architecture, and Radeon HD 4890 - with TeraScale.
  • Core clock speed of Radeon HD 4890 is 274 MHz higher, than GeForce 8800 GTX.
  • GeForce 8800 GTX is manufactured by 90 nm process technology, and Radeon HD 4890 - by 55 nm process technology.
  • GeForce 8800 GTX is 29 mm longer, than Radeon HD 4890.
  • Memory clock speed of Radeon HD 4890 is 3000 MHz higher, than GeForce 8800 GTX.

Game benchmarks

high / 1080p 0−1 7−8
ultra / 1080p 4−5
QHD / 1440p 0−1 0−1
low / 720p 1−2 16−18
medium / 1080p 0−1 8−9
The average gaming FPS of Radeon HD 4890 in Assassin's Creed Odyssey is 1600% more, than GeForce 8800 GTX.

Full Specs

  GeForce 8800 GTX Radeon HD 4890
Architecture Tesla TeraScale
Code name G80 RV790
Type Desktop Desktop
Release date 8 November 2006 2 April 2009
Pipelines 128 800
Core clock speed 576 MHz 850 MHz
Transistor count 681 million 959 million
Manufacturing process technology 90 nm 55 nm
Texture fill rate 36.8 billion/sec 34.00
Floating-point performance 345.6 gflops 1,360.0 gflops
Length 270 mm 241 mm
Memory bus width 384 Bit 256 Bit
Memory clock speed 900 MHz 3900 MHz
Memory bandwidth 86.4 GB/s 124.8 GB/s
DirectX 11.1 (10_0) 10.1 (10_1)
Shader Model 4.0 4.1
OpenGL 3.3 3.3
OpenCL 1.1 1.1
Vulkan N/A N/A
CUDA +
CUDA cores 575
SLI options +
  Check Price