NVIDIA GeForce RTX 40 “SUPER” GPUs Rumored To Be Unveiled At CES 2024

NVIDIA's GeForce RTX 40 "SUPER" GPU refresh is now rumored to be unveiled at CES 2024 which is just a few months away.

The NVIDIA GeForce RTX 40 "SUPER" GPUs seem to be very close to an official unveil as per the latest post by Kopite7kimi. Replying to a comment, the leaker states that the SUPER Refresh of GeForce RTX 40 GPUs is headed for an official unveiling at CES 2024. The event takes place in Las Vega, US, between the 9th and 12th of January.

CES

— kopite7kimi (@kopite7kimi) November 5, 2023

Most tech companies are present at CES 2024 but NVIDIA has yet to announce an official event or keynote during CES. There are also pre-shows that don't get listed very close to the event but given the GeForce RTX 40 SUPER GPU refresh is going to be a major product announcement for the tech company, there should be some noise made prior to the unveil. NVIDIA posted teasers of its last RTX 20 SUPER GPUs months prior to launch and people actually started doubting if the "SUPER" teaser was just a marketing tactic or an actual product launch.

What we know so far is that NVIDIA is expected to launch at least three graphics cards within its GeForce RTX 40 "SUPER" Refresh stack which would include the GeForce RTX 4080 SUPER, RTX 4070 Ti SUPER, and the RTX 4070 SUPER. These naming conventions are in no way finalized and so aren't the specifications or prices. NVIDIA makes and evaluates several SKUs prior to the release to avoid leaks of actual "launch" hardware so the rumors that you might be hearing up till now may or may not be true. What is true is the fact that most of the rumored SKUs do exist in some shape or form and show up after the launch of the official "retail" SKUs.

NVIDIA GeForce RTX 4080 SUPER Specifications (Rumored)

Starting at the top, we have the NVIDIA GeForce RTX 4080 SUPER which is rumored to use the AD103-400 GPU with the full 10,240 cores, 320 TMUs, 112 ROPs, and 64 MB of L2 cache. The chip will use a 256-bit bus interface which would suggest a 16 GB GDDR6X memory, same as the RTX 4080 Non-SUPER. So that suggests that NVIDIA has both 20 GB (AD102 / 320-bit) and 16 GB (AD103 / 256-bit) SKUs but what makes it to retail remains to be seen. The NVIDIA GeForce RTX 4080 Non-SUPER has a TBP of 320W so we can expect similar figures for the 4080 SUPER.

NVIDIA GeForce RTX 4070 Ti SUPER Specifications (Rumored)

Next up, we have the NVIDIA GeForce RTX 4070 Ti SUPER which Kopite7kimi believes is a really weird naming choice and to be honest, it kind of is. But as for the specifications, the card is said to feature AD103-275 / AD102-175 GPU SKUs with the same 8,448 cores across both variants and 48 MB of L2 cache. The GeForce RTX 4070 Ti SUPER should have a TBP close to the 285W mark of the existing 4070 Ti.

NVIDIA GeForce RTX 4070 SUPER Specifications (Rumored)

Lastly, there's the NVIDIA GeForce RTX 4070 SUPER which is said to come in AD104-350 or AD103-175 SKU configurations with the same 7,168 cores across both variants. The GPU is expected to get 48 MB of L2 cache. It looks like this card would stick with the 12 GB GDDR6X memory though we can expect NVIDIA to push the memory speeds up using better Micron DRAM which can reduce the stress on the lower 192-bit bus interface. For the RTX 4070 SUPER, the card will have a 20W higher TBP than the existing 4070 at 220W.

So to sum things up, the following is the core count bump as suggested by the rumor:

We are still a good few months away from a possible launch (2024), a lot can change so it's wise to take all of these with a grain of salt.