NVIDIA GeForce RTX 4xxx SUPER

NVIDIA is preparing the RTX 4xxx SUPER lineup, which will be presented on January 8 at the CES 2024 exhibition. After the presentation, NVIDIA will allow board partners to begin marketing campaigns for their respective lineups. A recent update has allowed leak specialists to learn about the delivery dates of these cards, which, as reported by ITHome, are already being prepared.

NVIDIA GeForce RTX 40 SUPER announcement: January 8.
NVIDIA GeForce RTX 4070 SUPER: January 17.
NVIDIA GeForce RTX 4070 Ti SUPER: January 24.
NVIDIA GeForce RTX 4080 SUPER: January 31.

The RTX 40 SUPER family of graphics cards will be presented on the same day, but their actual availability will vary. NVIDIA intends to launch all three products within January, with the RTX 4070 SUPER being the first to hit the market with a launch date of January 17, followed by the RTX 4070 Ti SUPER on January 24, and finally the RTX 4080 SUPER on January 31. All cards will be released a week apart, giving reviewers enough time for testing and partners time for marketing their latest products.

RTX SUPER

So far, there’s no word on NVIDIA’s own Founders Edition design. Partners will offer a range of new and updated non-reference designs, although NVIDIA has the opportunity to slightly refresh its design, possibly with a new “SUPER” logo.

The NVIDIA GeForce RTX 4080 SUPER, expected to use the AD103-400 (PG139 SKU 355) graphics processor with 10240 cores, 320 TMUs, 112 ROPs, and 64 MB of L2 cache memory. The chip will use a 256-bit bus interface, which suggests 16 GB of GDDR6X memory, the same as the RTX 4080. The NVIDIA GeForce RTX 4080 SUPER will have the same power as the RTX 4080 at 320 watts.

The video card is expected to be 3-5% faster than the RTX 4080, which is not a significant advantage, but custom models will provide a performance boost of almost 10%. NVIDIA has not yet determined prices for the SUPER lineup, but this slight increase in performance should help the card perform faster than the Radeon RX 7900 XTX, and if it is priced between $1000 and $1100, it will be very competitive.

The NVIDIA GeForce RTX 4070 Ti SUPER will be equipped with either the AD103-275 / AD102-175 (PG141 SKU 323) graphics processor with 8448 cores in both variants and 48 MB of L2 cache memory. The video card will also be equipped with 16 GB of GDDR6 memory, which is 4 GB more than the RTX 4070 Ti, and will support a 256-bit bus interface. The video card will retain a 285 watt TGP power, the same as the regular version.

In terms of performance, the NVIDIA GeForce RTX 4070 Ti SUPER 16 GB will provide an average performance increase of 15% compared to the non-SUPER variant and should compete well with the Radeon RX 7900 XT at a possibly lower price.

The NVIDIA GeForce RTX 4070 SUPER is said to come in AD104-350 or AD103-175 SKU (PG141 SKU 335) configurations with the same 7168 cores in both variants. The graphics processor is expected to receive 48 MB of L2 cache memory. It seems that this card will operate with 12 GB of GDDR6X memory through the same 192-bit bus interface. As for the RTX 4070 SUPER, the card’s TBP power will be 20 watts higher than the existing 4070 at 220 watts.

In terms of performance, the NVIDIA GeForce RTX 4070 SUPER is expected to be approximately 14% faster than the RTX 4070. The video card will also receive a new CEM 5.1 Gen5 power connector. Existing RTX 4070 video cards come either with an 8-pin or a 12-pin power connector (supplied with an adapter).

In terms of performance, the NVIDIA RTX 40 SUPER is expected to deliver approximately the following performance based on reference specifications:

RTX 4080 SUPER compared to RTX 4080: an average of 3-5% faster.
RTX 4070 Ti SUPER compared to RTX 4070 Ti: an average of 15% faster.
RTX 4070 SUPER compared to RTX 4070: an average of 14% faster.

It was previously stated that “Nvidia ends mass production of RTX 4070 Ti and RTX 4080.

The trio of NVIDIA GeForce RTX 40 SUPER will be presented at the CES 2024 exhibition, with a launch presumably in the same month.