GeForce RTX 3070 Ti vs Radeon RX 6900 XT

Intro

Compare those specs to the Radeon RX 6900 XT, which makes use of a 7 nm design. AMD has set the core frequency at 1825 MHz. The GDDR6 memory runs at a frequency of 2000 MHz on this particular card. It features 5120 SPUs along with 320 Texture Address Units and 128 Rasterization Operator Units.

Display Graphs

Hide Graphs

Power Usage and Theoretical Benchmarks

Power Consumption (Max TDP)

GeForce RTX 3070 Ti		290 Watts
Radeon RX 6900 XT		300 Watts
	Difference: 10 Watts (3%)

Memory Bandwidth

Theoretically speaking, the GeForce RTX 3070 Ti will be 19% faster than the Radeon RX 6900 XT overall, due to its greater data rate. (explain)

GeForce RTX 3070 Ti		622899 MB/sec
Radeon RX 6900 XT		524288 MB/sec
	Difference: 98611 (19%)

Texel Rate

The Radeon RX 6900 XT will be quite a bit (about 93%) better at texture filtering than the GeForce RTX 3070 Ti. (explain)

Radeon RX 6900 XT		584000 Mtexels/sec
GeForce RTX 3070 Ti		302400 Mtexels/sec
	Difference: 281600 (93%)

Pixel Rate

If running with high levels of AA is important to you, then the Radeon RX 6900 XT is the winner, by a large margin. (explain)

Radeon RX 6900 XT		233600 Mpixels/sec
GeForce RTX 3070 Ti		151200 Mpixels/sec
	Difference: 82400 (54%)

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

Specifications

Memory Bandwidth: Bandwidth is the max amount of information (in units of MB per second) that can be transferred across the external memory interface in a second. It is worked out by multiplying the bus width by its memory clock speed. If it uses DDR type memory, it must be multiplied by 2 once again. If it uses DDR5, multiply by 4 instead. The higher the card's memory bandwidth, the better the card will be in general. It especially helps with AA, HDR and high resolutions.

Texel Rate: Texel rate is the maximum texture map elements (texels) that can be applied in one second. This figure is calculated by multiplying the total amount of texture units by the core clock speed of the chip. The higher the texel rate, the better the card will be at texture filtering (anisotropic filtering - AF). It is measured in millions of texels in a second.

Pixel Rate: Pixel rate is the maximum number of pixels the graphics card could possibly write to the local memory in one second - measured in millions of pixels per second. The figure is calculated by multiplying the amount of colour ROPs by the the core speed of the card. ROPs (Raster Operations Pipelines - also called Render Output Units) are responsible for outputting the pixels (image) to the screen. The actual pixel fill rate also depends on quite a few other factors, most notably the memory bandwidth of the card - the lower the memory bandwidth is, the lower the ability to reach the maximum fill rate.