The NVIDIA GeForce RTX 400 SUPER GPU family is expected to be unveiled at CES 2024 in January, most reporters agree. During this event, the company will present the cards and it is also said that the launch date for the product line is already planned for January 2024 as well (although it could still be postponed due to NVIDIA’s internal decisions).
The NVIDIA GeForce RTX 4000 SUPER GPU family will actually include three cards that have already been leaked in recent weeks. These include the GeForce RTX 4080 SUPER, the RTX 4070 Ti SUPER (unfortunately, this atrocious naming has now been confirmed) and the RTX 4070 SUPER. All three cards are based on the NVIDIA Ada Lovelace graphics architecture and offer a range of upgrades, mainly in the form of better core configurations.
NVIDIA GeForce RTX 4080 SUPER
Starting at the top is the NVIDIA GeForce RTX 4080 SUPER, which is expected to use the AD103-400 GPU (PG139 SKU 355) with the full 10,240 cores, 320 TMUs, 112 ROPs and 64 MB L2 cache. The chip will use a 256-bit bus interface, which indicates 16 GB of GDDR6X memory, as in the RTX 4080 Non-SUPER. The NVIDIA GeForce RTX 4080 SUPER will have the same TGP as the RTX 4080 Non-SUPER with 320W. In terms of performance, the graphics card is expected to be about 3-5% faster than the RTX 4080 Non-SUPER, which is not a big gain. But customized models will deliver a performance increase of up to 10%. NVIDIA hasn’t yet committed to pricing for the SUPER series, but this small performance boost should help make the card faster than the Radeon RX 7900 XTX. If it were priced at around $1000-1100, that would be quite competitive.
NVIDIA GeForce RTX 4070 Ti SUPER
Next up, NVIDIA presents the new GeForce RTX 4070 Ti SUPER graphics card. It will be equipped with various AD103-275 / AD102-175 GPU SKUs (PG141 SKU 323), which offer a total of 8,448 cores and 48 MB L2 cache. Compared to the RTX 4070 Ti Non-SUPER, the graphics card will also have an upgrade to the VRAM and will now have 16 GB GDDR6 memory. It will also support a 256-bit bus interface. The TGP remains the same at 285 watts, which corresponds to the value of the non-SUPER variant. In terms of performance, the NVIDIA GeForce RTX 4070 Ti SUPER 16 GB GPU will offer an average increase of 15% compared to the non-SUPER variant. It will therefore be able to hold its own against the Radeon RX 7900 XT and may be available at a lower price.
NVIDIA GeForce RTX 4070 SUPER
The NVIDIA GeForce RTX 4070 SUPER will then also be available and will be offered in the configurations AD104-350 or AD103-175 SKU (PG141 SKU 335). The graphics card will be equipped with 7.168 cores and a 48 MB L2 cache. Interestingly, despite the 12 GB GDDR6X memory, the GPU will still have the 192-bit bus interface. Compared to the existing 4070, however, the RTX 4070 SUPER will have a TBP that is 20 watts higher, bringing the total to 220 watts. The NVIDIA GeForce RTX 4070 SUPER is expected to offer a performance increase of around 14% compared to the RTX 4070 Non-SUPER. In addition, the graphics card will be equipped with the new CEM 5.1 Gen5 power connector. The current RTX 4070 graphics cards are available with either an 8-pin connector or a 12-pin power connector (with adapter).
In terms of performance, we can therefore have the following expectations of NVIDIA’s RTX 40 SUPER GPUs (based on the respective reference specifications).
- RTX 4080 SUPER vs RTX 4080: On average 3-5% faster
- RTX 4070 Ti SUPER vs RTX 4070 Ti: 15% faster on average
- RTX 4070 SUPER vs RTX 4070: 14% faster on average
55 Antworten
Kommentar
Lade neue Kommentare
Urgestein
Urgestein
Mitglied
Urgestein
Urgestein
Mitglied
Mitglied
Urgestein
Urgestein
Mitglied
Urgestein
Mitglied
Urgestein
Mitglied
Veteran
Urgestein
Urgestein
Urgestein
Alle Kommentare lesen unter igor´sLAB Community →