A few days ago, a youtuber specializing in leaking information and speculating on future hardware dared to publicly state that an alleged NVIDIA Titan ADA, which would be its highest specification graphics card, and which will supposedly use a dual 16-pin connector, in the tests was melting the power supplies. Which we do not believe since advanced simulators are usually used for it. However, it is not the only nonsense that we have seen, however, all this needs an explanation
Will we see an NVIDIA RTX 4090 Ti or is it canceled?
In the midst of the rumor mill prior to the presentation of the new NVIDIA RTX 4000, we already knew that the graphics cards with the top-of-the-range GPU, AD102, would use the new connector, mostly due to the fact that we had already seen the 12VHPWR in the RTX 3090 You from a few months ago. The little difference in launch time between the RTX 3090 Ti and the RTX 4090 and the fact that the GA102 and AD102 chips have similar sizes already made us logically think that the PCB of both cards was going to be the same or almost the same.
And so it has been, not in vain, the name of the piece on which the components of one are mounted receives the code name of PG136 for that of the RTX 3090 Ti and that of the RTX 4090 has been baptized as PG136D. And at first glance they look the same, except for a number of small details. As is the lack of NVLink connector and the use of choke coils that allow a higher electrical power input. Which would mark us for a potential higher-end model, using all the power of the new connector, 600 W, instead of the 450 W currently used by the RTX 4090.
An additional clue could also be in the information of the maximum TGP supported by the BIOS of the RTX 4090, which everything indicates that it would be 660 W, which would require the base power of the PCI Express plus that of the new connector. However, the biggest clue is that the AD102 chip can have up to 144 SMs in its configuration, but the RTX 4090 has a configuration of 128.
So how come NVIDIA hasn’t released it?
Although the PCB of both graphics cards, RTX 3090 Ti and RTX 4090, is almost identical, NVIDIA has surprised us with a higher heatsink and fan. How is that possible if they supposedly move in the same range of consumption? Well, the simplest explanation is that the entire design of the RTX 4090 could be finer, but the engineers have decided to kill two birds with one stone and make a design for an eventual RTX 4090 Ti. The good thing is that this is going to be ideal for overclockers and we will see very interesting things in the future.
In any case, about its absence at launch, it is not surprising either, the same thing happened with its direct predecessor that came out 18 months after the launch of the RTX 30 and we did not tear our clothes. In any case, it must be clear that NVIDIA has all the elements to launch an RTX 4090 Ti at a given moment, but they do not need it at the moment. Also, that said card is not Titan ADA and will not require the use of a double connector to work, as many claim.
And speaking of TITAN Ada, what about her?
NVIDIA ditched the TITAN branding in the previous generation, however what has more numbers to come out is a professional graphics card, with full NVLink support and 48GB GDDR6X. More than anything due to the fact that in the face of AI professionally, 24 GB of memory falls short. In any case, the PC gaming market is not prepared to use consumption beyond 700 W only on the graphics card. This does not mean that we do not see custom cards with a double connector, as happened with the 3090 Ti and certain models.
In any case, seeing the size of the RTX 4090 for a consumption somewhat above 600 W, it is clear that the eventual TITAN ADA would have needed more complex solutions such as the use of liquid cooling. In any case, we do not believe that NVIDIA wants to go beyond a single 12 + 4-pin connector, at least in its own graphics cards designed to be installed in PCs for gaming. Is there a chance they’ll get ahead of themselves? Yes, if AMD with its RX 7900 XT passes its hand over the face of the RTX 4090.