NVIDIA Founders Edition cards for some of the latest GPUs have been sent out to reviewers. The RTX 4070 SUPER and 4080 SUPER are among these models set to receive this reference edition.
In terms of pricing, the RTX 4080 SUPER is slated to be priced at $999, which is $200 less than the launch price of the non-SUPER version, RTX 4080. NVIDIA appears to be confirming earlier speculations that the RTX 4080S and 4070TiS will replace the current models in their product lineup. The updated chart no longer includes references to these specific SKUs.
The RTX 4070 Ti SUPER is set to take the place of the RTX 4070 Ti non-SUPER at a price point of $799. Simultaneously, the RTX 4070 SUPER is expected to be priced at $599 in retail, while the existing non-SUPER model is officially confirmed to have a revised MSRP of $599.
GeForce RTX 40 SUPER pricing, Source: NVIDIA
As we saw before, NVIDIA is focusing on the performance of their shaders, ray tracing, and tensor cores instead of their CUDA core specs. Nevertheless, NVIDIA RTX 4080 SUPER is to feature 10240 CUDA cores, 16GB GDDR6X memory (23 Gbps) and TGP (Total Graphics Power) of 320W. But NVIDIA claims that this model will actually require only around 246W when playing and 15W when idle. NVIDIA marketing claims that this card offers “4K Full RT Gaming and Super-Fast Gen AI” but also 2x the performance of RTX 3080Ti (more on that in the paragraph below). The RTX 4080 SUPER will launch on January 31.
The RTX 4070 Ti SUPER is to feature 8448 CUDA cores and 16GB GDDR6X memory. While it ships with a TGP of 285W, the average gaming power is estimated at 226W and 12W when the card is idle. The memory upgrade is undoubtedly the most noteworthy feature of this SKU. NVIDIA claims that RTX 4070 Ti SUPER will offer “2.5x the performance of RTX 3070 Ti”, but one should not be deceived, as this data is referring to DLSS Frame Generation support in some titles. Officially, RTX 4070 Ti SUPER launches on January 24th.