Nvidia to ‘Release’ 12GB RTX 4080, Saying It’s ‘Misnamed’

Nvidia announced today that it will be “closing “the 12GB version of its upcoming GeForce RTX 4080 series GPU on the grounds that “having two GPUs with the 4080 designation is confusing.”The map will not launch in its originally scheduled November window, but it will return at some point after the rebrand.

“The RTX 4080 12GB is a fantastic graphics card, but it’s misnamed,”says a brief, anonymous Nvidia blog post. The 16GB version of the 4080 will still launch on November 16th.

The 16GB version of the 4080 was in line with previous Nvidia xx80-series cards – it used the same GPU die as the high-end RTX 4090, but with some CUDA cores disabled and a lower clock speed. But the difference between the 12GB and 16GB versions of the 4080 was much wider than their names might suggest; the 12 GB version had far fewer CUDA cores and a narrower 192-bit memory bus, and was rumored to use a completely different GPU die. Tests from Nvidia have shown that the 12GB version can be up to 30% slower than the 16GB version of the 4080.

The most likely course of action is for Nvidia and its partners to rebrand and rebrand all existing 12GB RTX 4080 cards to some sort of RTX 4070 variant. This will most likely have absolutely no impact on card performance or price. But it will bring the branding of the card more in line with past generations, perhaps removing some of the confusion from people wondering why two cards with the same model number have such different performance.