A few days before the presentation of the RTX 40, the next graphics cards from NVIDIA, the specifications have already leaked. partial specifications of the RTX 4090, RTX 4080 16GB and RTX 4080 12GB. So, the only thing that would await us is to know the architectural changes and novelties in this aspect that the Ada Lovelace architecture brings compared to the current one. Which models have been leaked and how are each presented?
For NVIDIA there is a daunting task in the coming months, the launch of its new generation of graphics cards for PC gaming is compounded by the problem of the definitive end of the mining bubble and the flooding of the market of models RTX 30 That’s why they decided to start with the most powerful models, at the moment, in an almost repeated launch with three card models appearing in the top of the range.
These are the models that launch the next generation of NVIDIA
In total, three would be the models that NVIDIA will launch to release its RTX 40 cards, once again repeating what we have already seen in the last two generations of graphics cards. Out of curiosity, there is a last minute name change to one of the models, as happened a few years ago when the rumored RTX 3080 Ti evolved into the RTX 3090 we all know. In this case it is the RTX 4070 which made the jump to be called the 12GB RTX 4080. Hopefully this change doesn’t affect the final price as well, which we still don’t know, but seeing the photo, we better keep our fingers crossed.
RTX-4090
The most powerful is the RTX 4090, it will have a wide variety of different models and will appear with the AD-102-300 chip with 16,384 CUDA “cores”, i.e. 32-bit floating point units. what they mean 128 SM if there were no configuration changes unknown to us. By the way, one thing we don’t know yet is his base speed, but we do. we know that of Boost, 2520 MHz. Below the 3000 MHz or 3 GHz that were speculated a few weeks ago. Its memory is 21 Gbps GDDR6X for bandwidth > 1 TB/s. Although what is striking is the margin of its TGP, which will apparently increase from 450 W to 660 W.
RTX 4080 16GB
In the middle of the table will be the RTX 4080 with the AD-103-300 chip and with 9,728 CUDA “cores”, and therefore 76 SM, a Boost speed of 2505 MHz and 16 GB of GDDR6X memorybut to 23 Gbpsyes, that is to say, 736 GB/s bandwidth. Its TGP is 340 Wbut in the map design you can access the 516W. The fact that it does not reach the maximum configuration possible with the AD103 chip makes us think that there is a variant called AD103-450 which would be the RTX 4080 Ti and would be released much later.
With said TGP, the initial model would not need the 12+4 pin connector work, because it would not differ in this aspect compared to the current graphics. On the other hand, future models approaching the maximum consumption and temperature capabilities of this model could prevail. In any case, everything seems to indicate that this is the limit for the card plate and its components to support the eventual RTX 4080 Ti. Which makes us think that it could be the same with the model that we previously mentioned regarding a possible RTX 4090 Ti. Anyway, we would only have to wait a few days.
RTX 4080 12GB
Despite the name, it’s not a cut in terms of the amount of memory from the 16GB RTX 4080, since the 12GB model uses a different chip, but obviously with the same architecture, the AD-104-400 with 7680 CUDA “hearts”, 60 SM and one Boost the 2610MHz of speed Its capacity is 12 GB and it uses GDDR6X memory at 12 Gbpswhich results in a 504 GB/s bandwidth. As for the consumption of the card, it oscillates between 285 W and 366 W.
Table of Contents
