Compare any two graphics cards:

Geforce GTX 680 vs Radeon HD 6970

Intro

The Geforce GTX 680 features core speeds of 1006 MHz on the GPU, and 1502 MHz on the 2048 MB of GDDR5 memory. It features 1536 SPUs along with 128 Texture Address Units and 32 ROPs.

Compare all that to the Radeon HD 6970, which uses a 40 nm design. AMD has clocked the core frequency at 880 MHz. The GDDR5 memory works at a frequency of 1375 MHz on this card. It features 1536 SPUs as well as 96 TAUs and 32 Rasterization Operator Units.

Display Graphs

Hide Graphs

Benchmarks

These are real-world performance benchmarks that were submitted by Hardware Compare users. The scores seen here are the average of all benchmarks submitted for each respective test and hardware.

3DMark Fire Strike Graphics Score

Geforce GTX 680		7650 points
Radeon HD 6970		3470 points
	Difference: 4180 (120%)

Power Usage and Theoretical Benchmarks

Power Consumption (Max TDP)

Geforce GTX 680		195 Watts
Radeon HD 6970		250 Watts
	Difference: 55 Watts (28%)

Memory Bandwidth

In theory, the Geforce GTX 680 should perform just a bit faster than the Radeon HD 6970 overall. (explain)

Geforce GTX 680		192256 MB/sec
Radeon HD 6970		176000 MB/sec
	Difference: 16256 (9%)

Texel Rate

The Geforce GTX 680 is a lot (more or less 52%) faster with regards to texture filtering than the Radeon HD 6970. (explain)

Geforce GTX 680		128768 Mtexels/sec
Radeon HD 6970		84480 Mtexels/sec
	Difference: 44288 (52%)

Pixel Rate

The Geforce GTX 680 will be a little bit (approximately 14%) better at anti-aliasing than the Radeon HD 6970, and also will be capable of handling higher screen resolutions better. (explain)

Geforce GTX 680		32192 Mpixels/sec
Radeon HD 6970		28160 Mpixels/sec
	Difference: 4032 (14%)

Please note that the above 'benchmarks' are all just theoretical - the results were calculated based on the card's specifications, and real-world performance may (and probably will) vary at least a bit.

Price Comparison

Display Prices

Hide Prices

Geforce GTX 680

Amazon.com

Check prices at:

Radeon HD 6970

Amazon.com

Check prices at:

Please note that the price comparisons are based on search keywords - sometimes it might show cards with very similar names that are not exactly the same as the one chosen in the comparison. We do try to filter out the wrong results as best we can, though.

Specifications

Display Specifications

Hide Specifications

Model	Geforce GTX 680	Radeon HD 6970
Manufacturer	nVidia	AMD
Year	March 2012	December 2010
Code Name	GK104	Cayman XT
Memory	2048 MB	2048 MB
Core Speed	1006 MHz	880 MHz
Memory Speed	6008 MHz	5500 MHz
Power (Max TDP)	195 watts	250 watts
Bandwidth	192256 MB/sec	176000 MB/sec
Texel Rate	128768 Mtexels/sec	84480 Mtexels/sec
Pixel Rate	32192 Mpixels/sec	28160 Mpixels/sec
Unified Shaders	1536	1536
Texture Mapping Units	128	96
Render Output Units	32	32
Bus Type	GDDR5	GDDR5
Bus Width	256-bit	256-bit
Fab Process	28 nm	40 nm
Transistors	3540 million	2640 million
Bus	PCIe 3.0 x16	PCIe x16
DirectX Version	DirectX 11.0	DirectX 11
OpenGL Version	OpenGL 4.2	OpenGL 4.1

Memory Bandwidth: Bandwidth is the maximum amount of data (in units of megabytes per second) that can be moved over the external memory interface in one second. The number is calculated by multiplying the card's bus width by the speed of its memory. If it uses DDR memory, it should be multiplied by 2 again. If it uses DDR5, multiply by 4 instead. The higher the card's memory bandwidth, the faster the card will be in general. It especially helps with anti-aliasing, HDR and higher screen resolutions.

Texel Rate: Texel rate is the maximum texture map elements (texels) that are processed in one second. This figure is worked out by multiplying the total number of texture units by the core clock speed of the chip. The higher the texel rate, the better the video card will be at handling texture filtering (anisotropic filtering - AF). It is measured in millions of texels processed in one second.

Pixel Rate: Pixel rate is the most pixels the video card could possibly record to the local memory per second - measured in millions of pixels per second. The figure is worked out by multiplying the number of Raster Operations Pipelines by the the core speed of the card. ROPs (Raster Operations Pipelines - also sometimes called Render Output Units) are responsible for outputting the pixels (image) to the screen. The actual pixel fill rate is also dependant on many other factors, especially the memory bandwidth of the card - the lower the bandwidth is, the lower the potential to get to the maximum fill rate.

Display Prices

Hide Prices