NVIDIA abandons the GeForce RTX 4080 12GB

By presenting two 12GB and 16GB versions of its GeForce RTX 4080 a few weeks ago alongside the RTX 4090, NVIDIA clearly failed to convince the general public. The manufacturer is trying to correct the situation by canceling the RTX 4080 12GB.

©NVIDIA

For a few generations of graphics cards, NVIDIA has applied itself to launching a 90 or TITAN model as a technological showcase, an 80 model at the top of the range, then the 70 and following models. For Ada Lovelace, the manufacturer chose to present two RTX 4080 with sufficiently different characteristics – down to the onboard GPU – for doubt to arise: is it really an RTX 4080 12GB or rather an RTX 4070 (Ti) too expensive to officially bear this name? Or is it the RTX 4080 16GB which is actually a Ti model that doesn’t mean it?

The RTX 4080 12GB canceled or… renamed?

One thing is certain, NVIDIA intends to put an end to this confusion in the minds of the general public; the manufacturer has just canceled the RTX 4080 12GB. Only the GeForce RTX 4080 16GB should therefore be available from November 16 to complete the catalog of Ada Lovelace cards.

All the same, it remains to be seen which name NVIDIA will finally choose for this graphics card which is supposed to be slower than the RTX 3090 Ti by about 11% in 4K. A certain volume of RTX 4080 12GB has undoubtedly already left the factories, and it therefore seems unlikely that this card will be canceled altogether. On the other hand, we can expect the manufacturer to retain these characteristics and simply change the name of the card. But that would require NVIDIA’s partners to review their copy on the packaging and bundle side, and to throw away all the boxes of RTX 4080 12GB already manufactured…

Related Articles:  Producer of “The Legend of Zelda: Tears of Kingdom” wants a franchise movie after the success of the Mario Bros. movie | Nintendo | Nintendo Switch | DEPOR-PLAY
Graphic card GeForce RTX 4090 GeForce RTX 4080 16 Go GeForce RTX 4080 12 Go
SKU PG139-SKU330 PG139-SKU360 PG141-SKU331
Architecture Yes (TSMC 4N) Yes (TSMC 4N) Yes (TSMC 4N)
GPU AD102-300 AD103-300 AD104-400
Stream Multiprocessors 128 76 60
Hearts CUDA 16 384 9728 7680
Frequency boost 2520 MHz 2505 MHz 2610 MHz
VRAM 24 Go G6X 16 Go G6X 12 Go G6X
Memory bus 384-bit 256-bit 192-bit
Memory speed 21 Gbit/s 22,5 Gbit/s 21 Git/s
Memory bandwidth 1008 Go/s 720 Go/s 504 Go/s
Default TGP 450W 320W 285W
Max TGP 660W 516W 366W
MSRP 1599 dollars
1949 euros
1199 dollars
1469 euros
899 dollars

NVIDIA driver supports new GeForce RTX 3000

Source : NVIDIA

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.