How the RTX 4090 and 4080 Compare to the RTX 3090 Ti and 3080 Ti
After months of rumors and teasing, Nvidia finally announced the RTX 40-series of graphics cards during its GTC 2022 keynote. Using the new Ada Lovelace graphical architecture, the RTX 40-series will serve as a successor to the RTX 30-series, which debuted back in 2020.
With the RTX 40-series set to launch less than a month from now, let’s take a look at the specs, dig into the standout features, and see how the first GPUs in the RTX 40 family stack up against the RTX 3090 Ti and the RTX 3080 Ti.
RTX 40 vs. RTX 3090 Ti and 3080 Ti: Brief Overview
As the infographic above notes, many changes are coming from the RTX 30-series to the RTX 40-series. However, the specs are not all different from the Ti variants of the RTX 3090 and 3080, and the RTX 40-series all use GDDR6X memory.
Nvidia claims that the RTX 4080 variants will provide two to four times the performance of the RTX 3080 Ti. Meanwhile, the RTX 4090 Ti is claimed to be two to four times faster than the RTX 3090 Ti.
Other similarities worth pointing out include the GPUs supporting hardware-based ray tracing in addition to Nvidia’s supersampling tech, DLSS. While the RTX 30-series supports DLSS, there are some differences that we’ll discuss in the next section.
Another interesting note is that there are two variants of the RTX 4080: one with 16GB of GDDR6X memory, which will retail for $1,199, and another with 12GB of GDDR6X memory that will cost $899. This would not be the first time Nvidia did this, as the company released two different versions of its RTX 3080 graphics cards – the launch model included 10GB of memory, while another version released nearly two years later included 12GB of memory.
But memory (and pricing) isn’t the only difference between the two RTX 4080 variants. The 16GB model has more RT, Tensor, and CUDA cores and requires at least 750W of power. In contrast, the 12GB model has a higher base and boost clock and requires at least 700W of power.
RTX 40 vs. RTX 3090 Ti and 3080 Ti: Architecture
The RTX 30-series is built on Nvidia’s Ampere graphical architecture, which uses Samsung’s 8nm technology. The RTX 40-series, meanwhile, is built on the new Ada Lovelace architecture, which uses TSMC’s 4nm N4 technology.
The Ampere architecture is the second generation of RTX, which uses third-generation Tensor and second-generation RT cores. The Ada Lovelace architecture, named after the mathematician and writer, is the third generation of RTX, using fourth-gen Tensor cores and third-gen RT cores. And as you expect with a new generation of microarchitecture, every Lovelace RT and Tensor core is more powerful than every Ampere RT and Tensor core.
Lovelace architecture is also the only graphical architecture to support the new third generation of DLSS. Nvidia noted in a blog post that DLSS 3 is “powered by the new fourth-generation Tensor Cores and Optical Flow Accelerator,” which are exclusively found in the RTX 40-series.
Of course, these comparisons only tell the story on paper, and we won’t know how the GPUs truly compare until we have the opportunity to benchmark the RTX 40-series ourselves. Still, the new fabrication process and graphical architecture show promising signs that this will likely be a nice leap in performance between the two generations of GeForce graphics cards.
Taylor is the Associate Tech Editor at IGN. You can follow her on Twitter @TeamNixster.