The Nvidia RTX 4080 graphics card with 16GB of VRAM – the high-end model, as opposed to the 12GB version – was spotted in a supposed 3DMark benchmark, giving us an idea of its gaming performance.
Now, we should make it clear up front that it’s just that – a performance notion, more on that later – and we should be careful in assuming it’s genuine too. Could be fake, and how VideoCardz (opens in new tab), which scored the benchmark, points out, there are doubts as to how a working driver with support for the GPU was achieved. (Unlike the upcoming RTX 4090, the RTX 4080 graphics cards don’t come out until November.)
So there are some thick question marks around that, and the source, the chipell (opens in new tab) forums in China is also not the most reliable, although there have been some genuine leaks in the past.
In the graphics scores (in 4K resolution) the RTX 4080 supposedly achieved it in 3DMark, which were 17,465 on FireStrike Extreme and 13,977 on TimeSpy Extreme. Looking at the comparative scores of the RTX 3080 (12GB), this makes the RTX 4080 around 50% faster in both respects.
Another 3DMark Port Royal result was also highlighted, with the RTX 4080 hitting 17,607, which is about 45% faster, again pretty much the same level.
As a side note, in the images provided, the specs are shown with the RTX 4080 clocked at 2.5GHz.
Analysis: Let’s wait and see – but pricing concerns certainly abound
At the risk of sounding like a broken disk, as we always remind people with these types of leaks, it’s just a synthetic benchmark – what we really need to judge a GPU is testing on real games, and a wide variety of them too (like the results can vary greatly with different games and, in this case, graphics settings).
There is actually a gaming benchmark delivered by this leak in the form of Shadow of the Tomb Raider, where the RTX 4080 reached 128 frames per second at 4K resolution. While we don’t have a point of comparison for this – and none of the graphical details – at first glance this looks like a pretty decent result.
While some people online were a little disappointed with the 3DMark scores here, they are in line with what we really expected – and what we should also remember is that unstable drivers are likely at play. When official support arrives in the RTX 4080 release driver, the GPU will certainly be faster to some extent. And of course that’s before we start talking about other benefits like DLSS 3, which seems to be a big boost for games that support the technology (RTX 3000 GPUs won’t have this, by the way, although it could make it to the Ampere range eventually. ).
Of course, this whole leak could be made up, but there’s a fair amount of material and images here, so if it’s fake, someone’s had a bit of trouble (remember, it wouldn’t be the first time it’s happened). So let’s be cautious of this leak, and if true, equally cautious about the potential performance the RTX 4080 is achieving here, as the GPU will be faster at launch (or something really would go very, very wrong).
Probably the reason there was a negative reaction to this leak in some quarters is to look at this approximate 50% performance gain and compare it to what is a big perceived increase in price. But in reality, if we look at the cheapest 12GB RTX 3080 models right now (the GPU used in the performance comparisons above), the RTX 4080 has a relative price increase of around 60% for that performance boost of 50%.
That still means the Lovelace GPU is more expensive in terms of performance per dollar, but not by much. And hopefully, as mentioned, when the full speed of the released RTX 4080 is reached, it can pretty much be an overall value proposition in terms of performance.
Which is still not great, mind you, as graphics cards are still pretty expensive in our book and the tomes of many others – and of course there’s also the reality that the RTX 4080 16GB can be more expensive than the MSRP when it first breaks the cover. However, we seriously hope not, but these days, it seems almost unrealistic to expect recommended prices to hold at GPU launch. Initial stock levels will, of course, be a big determining factor here…