At its GPU Technology Conference (GTC) 2022 event, Nvidia launched its RTX 40 series desktop GPUs based on the Ada Lovelace architecture. The lineup consisted of the $1,599 flagship RTX 4090, along with two RTX 4080 SKUs, the RTX 4080 16GB model for $1,199 and the 4080 12GB model for $899.

VRAM capacity and bandwidth aren’t the only thing different between the two cards though, as Nvidia has reduced the number of 12 gig CUDA cores quite significantly compared to the 16GB 4080 model. In general, that is a reduction of more than 20% for the core count. Meanwhile, bandwidth is further impacted as it is reduced by more than 30%.

While Nvidia has done this type of naming before, for example with the GTX 1050 3GB model or the GTX 1060 3GB variant, the core count difference and overall performance difference between two of these variants has never been so great. Therefore, the company has rightly received criticism this time about this 12GB 4080 situation from the media and enthusiasts, as naming such a stripped down product the 16GB 4080 model makes little to no sense and is extremely misleading.

Nvidia seems to have realized the problem and has withdrawn the release of the RTX 4080 12 GB model, which was supposed to launch next month, on the 16th. The company writes:

The RTX 4080 12GB is a fantastic graphics card, but it’s not named correctly. Having two GPUs with the 4080 designation is confusing.

So, we’re hitting the “unroll” button on the 12 GB 4080. The RTX 4080 16GB is amazing and well on its way to delight gamers around the world on November 16.

For now, it’s unclear what Nvidia will call the 12GB 4080. Perhaps you’ll settle for something like the RTX 4080 Lite edition or perhaps an RTX 4070 Ti.

Source: Nvidia