Skip to main content

At this point, we know just about everything about Nvidia’s new GPUs

The leaks on Nvidia’s new Super GPUs are getting out of hand. The slow drip of information has been steady for many months, leaving very few details on the cards when they actually get announced.

We’re talking about the RTX 4080 Super, RTX 4070 Ti Super, and RTX 4070 Super, which will be the first three models in the lineup. Thanks to various retailers and distributors all around the globe, we already have a substantial amount of information about the upcoming GPUs. The information might not all be perfect, but it paints a pretty clear picture of what these cards will be like.

Recommended Videos

ho-ho- pic.twitter.com/i13OUuPhBh

— 188号 (@momomo_us) December 25, 2023

The RTX 4080 Super is expected to feature a modest speed increase to 23Gbps for its 16GB GDDR6X memory. This will result in a 2.6% boost in bandwidth, achieving 736GB/s across the 256-bit memory bus. On the other hand, the RTX 4070Ti/4070 Super will continue to utilize a 21Gbps memory speed.

The clock speeds will also see minor adjustments, with the RTX 4080 Super moving from 2205/2505 MHz (base/boost) to 2295/2550 MHz compared to the non-Super version. The RTX 4070 Ti Super and RTX 4070 Super are expected to maintain identical boost clocks to the original models (2610 MHz and 2475 MHz, respectively). There is only a minor change to the base clocks, now registering at 2340MHz and 1980MHz.

Leaked retailer listing of upcoming MSI RTX 40 Super GPUs.
Videocardz

Power consumption or TDP specifications are said to be 320W for the RTX 4080 Super, 285W for the RTX 4070Ti Super, and 220W for the RTX 4070 Super. Essentially, only the RTX 4070 Super will experience a small 20W increase in power consumption. The 12VHPWR power connector makes a comeback, but sadly, none of the leaked custom models are powered by standard connectors, meaning that Nvidia might be forcing its partners to utilize the high-power connector.

All of the specifications mentioned above are based on leaks and speculations, so things could obviously change or be wrong.

Notably, various RTX 40 Super series GPU models from popular board partners, including Asus, Gigabyte, and MSI, have been spotted online. MSI is expected to bring at least 12 new models, four from each SKU. There was also a recent leak where the Asus RTX 4070 Super Dual OC Edition was spotted by @momomo_us on X/Twitter.

A teaser shared by Gigabyte for its upcoming RTX 40 Super series GPUs.
Gigabyte

More recently, Aorus (Gigabyte’s gaming division) released a teaser for an upcoming GPU that will be showcased at CES. While we cannot decipher which GPU is in the teaser picture, it seems to be similar to Gigabyte’s Aorus Master series featuring ‘Windforce bionic shark’ fans and an RGB ring around each fan.

The teaser comes just a day after an EEC filing revealed Gigabyte’s entire inventory of upcoming GeForce RTX 40 Super GPUs. The company is expected to go all-in with a minimum of 10 RTX 4080 Super, 11 GeForce RTX 4070 Ti Super, and 12 GeForce RTX 4070 Super cards.

Nvidia is scheduled to deliver a special address on January 8 — and although the invite doesn’t mention what will be announced — it’s pretty clear what’s coming.

Judging by the various leaks and hints in the past few months, the RTX 40 Super-series will debut in January 2024. While this might be disappointing for enthusiasts hoping for an early RTX 50 series release, it is good news for those who took the wise decision of not buying an RTX 40-series GPU. It is also interesting as we haven’t seen a Super refresh ever since the RTX 20-series.

Of course, actual performance is still central, and that’s really all that’s left to know about these new cards. Nvidia is bound to make some claims about performance, but it won’t be until independent reviews come out that we know exactly how powerful they really are.

Kunal Khullar
Kunal Khullar is a computing writer at Digital Trends who contributes to various topics, including CPUs, GPUs, monitors, and…
Nvidia’s RTX 5070 Ti could displace the RTX 5080 — but I’m worried about it
Two RTX 4070 Ti Super graphics cards sitting next to each other.

Nvidia's RTX 5070 Ti is mere days away. Set to launch on February 20, the GPU marks the beginning of Nvidia's mainstream RTX 50-series. With similar specs to the RTX 5080, the RTX 5070 Ti has every chance to rank high among the best graphics cards -- but it's also going to face a number of obstacles that might impact its success.

Thanks to some leaked benchmarks, we now have a better idea of how the card might perform, and that rough ballpark is really a bit of a mixed bag. Here's why I think the RTX 5070 Ti might have an uphill climb when it first hits the shelves, but also why it might completely displace the RTX 5080.
Promising benchmarks -- well, kind of

Read more
Nvidia to expand RTX 50-series with more GPUs for budget gamers
Side view of the RTX 4060

Recent filings with the Eurasian Economic Commission (EEC) by popular GPU manufacturer Zotac (spotted by @harukaze5719 on X), have unveiled potential new additions to Nvidia's RTX 50-series lineup - the RTX 5050, RTX 5060, and RTX 5060 Ti. These registrations suggest that Nvidia is preparing to introduce budget-friendly options within its latest GPU series.

The RTX 5050 is particularly noteworthy, as it would mark Nvidia's potential return to the sub-$250 GPU market—a segment it hasn't actively targeted since the RTX 3050. The absence of a 50-class card in the RTX 40-series left a gap that was filled by older RTX 30-series GPUs and offerings from competitors. The introduction of the RTX 5050 could provide an affordable entry point for gamers seeking to leverage Nvidia’s latest technologies without a significant financial outlay.

Read more
Nvidia’s AI obsession is causing delays in its PC business
Logo on the Nvidia GeForce RTX 5080.

Component manufacturer, Nvidia appears to be short on GeForce RTX 50 series GPUs for laptops, which were originally set to launch in January.

Reports indicate that the supplier has been so focused on developing AI Chips that other parts of its business have lapsed. This has caused delays in supplying the GeForce RTX 50 Series chips to computing partners.

Read more