Skip to main content

Nvidia’s RTX Super might be a massive boost at no extra cost

The PNY RTX 4080 XLR8 installed in a PC.
Jacob Roach / Digital Trends

We just got another round of leaks surrounding the rumored Nvidia RTX 40 Super lineup. This time, the sources speak about the amount of memory these new GPUs might serve up. Nvidia may be making progress toward rivaling some of AMD’s best graphics cards, which typically have a lot more VRAM. But is this upgrade really going to be as significant as some speculate? Not all reputable sources agree.

A third source has just weighed in on the matter of the rumored RTX 4080 Super, RTX 4070 Ti Super, and the RTX 4070 Super. Benchlife cites its own sources at Nvidia’s board partners as it claims that the RTX 4080 Super might come with 20GB of memory, whereas the RTX 4070 Super might be boosted to 16GB. Doing so would definitely require chip changes for both cards. The RTX 4080 Super would now share the same AD102 GPU as the flagship RTX 4090, and the RTX 4070 Super would be bumped up to the AD103 chip found in the RTX 4080.

Recommended Videos

These are sizable upgrades that we’re talking about here. The RTX 4080 Super would receive 25% extra memory and a wider 320-bit bus. Switching to the AD102 chip also opens up the possibility of an increase in CUDA cores. Overall, this GPU would bridge the gap between the RTX 4080 and the RTX 4090.

Get your weekly teardown of the tech behind PC gaming
Check your inbox!

The RTX 4070 Super marks an interesting change. If it does switch from the AD104 to the AD103 chip, it might end up with better specs than the RTX 4070 Ti, which runs on AD104 and has 12GB of VRAM across a 192-bit bus. Where does that leave the RTX 4070 Ti Super, if that’s going to be a thing? Most likely also only the AD103 GPU, which makes this a pretty crowded chip. We could end up with three graphics cards where the performance jump from one to the next isn’t that big, although the gap between the RTX 4070 Super and the RTX 4080 should still be significant.

I have some different opinions.
I think the relationship between RTX 4080 Super and RTX 4080 is similar to that between RTX 2080 Super and RTX 2080. https://t.co/LJqKZRISta

— kopite7kimi (@kopite7kimi) October 23, 2023

While Benchlife’s report is interesting, well-known leaker kopite7kimi disagrees with these rumors. According to kopite7kimi, the refresh isn’t going to be as big a deal as the previous leaks suggested. This speculation is leaning more toward a minor enhancement that unlocks the full potential of the GPU and boosts memory speed. In fact, kopite7kimi believes that the RTX 4080 Super will max out the AD103 chip instead of being upgraded to AD102, and that change can’t possibly result in any major performance increase. The RTX 4070 Super is said to be a slightly cut-down version of the RTX 4070 Ti.

Seeing as the rumors have been consistent that the new RTX 4080 Super might cost the same as the current RTX 4080 ($1,200), the minor upgrade seems more consistent with what Nvidia usually does. We’ll have to wait and see.

Monica J. White
Monica is a computing writer at Digital Trends, focusing on PC hardware. Since joining the team in 2021, Monica has written…
Nvidia’s DLSS 4 can ‘see into the future’
nvidia dlss 4 announcement day 0 game app support

Alongside the announcement of its new RTX 5090, 5080, 5070 Ti, and 5070 GPUs at CES 2025, Nvidia revealed its next version of the wildly popular Deep Learning Super Sampling, or DLSS. Nvidia has expanded DLSS several times over the past few years, and DLSS 3, which is available today, is already a mainstay in hundreds of PC games. DLSS 4 looks to push that even further, which is where its ability to "see into the future" comes into play.

Promising neural rendering capabilities, DLSS 4 is one of the key features of Nvidia's new range of RTX 50-series graphics cards. DLSS 4 introduces Multi Frame Generation, an AI-driven technology that is said to significantly enhance gaming performance by generating up to three additional frames for each rendered frame. Essentially, it can predict

Read more
Nvidia promises RTX 4090 performance in a $1,300 laptop
Nvidia CEO Jensen Huang holding an RTX 50 GPU and a laptop.

Nvidia CEO Jensen Huang just unveiled the RTX 50-series, including both desktop cards like the beastly RTX 5090 and laptop variants. As far as laptop gamers go, there's a lot to get hyped for here, as these GPUs might end up being some of the best graphics cards in terms of performance. Huang promises to deliver RTX 4090-level performance in a $1,300 laptop, and that's at half the thermal design power (TDP).

During the CES 2025 keynote, Huang spoke about the various GPUs that are on the way to laptops. Availability starts in March, and although no precise release dates have been given yet, we know what to expect in terms of pricing, and we also have a bit of a clue about the performance.

Read more
Nvidia’s RTX 5090 is just as insane as you think — it’s $2,000 and twice as fast as the RTX 4090
A range of Nvidia RTX 50-series graphics cards.

Part of me thought the rumors about Nvidia's RTX 50-series GPUs were wrong. But the RTX 5090 is just as insane as everyone said it would be. Nvidia CEO Jensen Huang took to the stage at CES 2025 to officially kick off the show, announcing the RTX 5090, which clocks in at a staggering $2,000.

The monstrous graphics card has been the topic of rumors and speculation for well over a year. The entire range of Blackwell GPUs seemed to slipped out of a release late last year, as rumors up to that point had suggested. The RTX 5090 marks a $400 increase over the RTX 4090 we saw in the previous generation.

Read more