Two unreleased NVIDIA GeForce RTX 40 Founders Edition graphics cards, the RTX 4070 Ti and RTX 4060 Ti, have been photographed. We begin with images of the PCB and cooling for the NVIDIA GeForce RTX 4070 Ti Founders Edition graphics card. Most of you will recall that the card was not given the FE or Founders Edition treatment when it was first released, with the green team focusing on custom variants.
This is because the RTX 4070 Ti was originally going to be called the RTX 4080 12 GB, but the card received a lot of flak for using the 4080 naming scheme while offering a much lower and different performance tier than the RTX 4080 16 GB.
Because of the sudden “Unlaunching” and rebadging of the card, NVIDIA had little time to produce enough RTX 4070 Ti Founders Edition coolers for the launch, which was only a few weeks away, and thus decided to keep it an AIB-only option. However, this does not preclude NVIDIA from producing a Founders Edition model. The card featured a FE PCB and a cooling design.
With an 8+2+1 phase PCB design and a single 16-pin connector to boot it, the PCB was very compact. The GPU cooler was also shorter than the cooling solution used for the RTX 4080 and RTX 4090 cards, with a copper base plate and numerous aluminium cooling fins surrounding the shroud, as well as a flow-through fan design with two fans.
The second card pictured by the same leaker, KittyYYuko, is the NVIDIA GeForce RTX 4060 Ti graphics card, for which we only see the cooler.
The card says GeForce RTX 4060, but the leaker is certain it is the 4060 Ti, and we suspect it is a prototype FE model compatible with both the RTX 4060 Ti and RTX 4060 graphics cards. The RTX 4060 (Ti) graphics card has a flow-through design and a dual-slot form factor.
This FE variant appears to be much shorter than the RTX 4080 and RTX 4090 cards, and the aluminium die-cast frame is thicker and has a more matte appearance than the high-end cards’ metallic and shiny surfaces. This card appears to use the 16-pin connector as well, but with a TDP rating close to 200W, as previously reported.
The GeForce RTX 4060 Ti is expected to use the AD106-350-A1 GPU core, a scaled-down version of the full AD106 graphics chip, with 34 SMs or 4352 CUDA cores, an 8 GB GDDR6 memory running at 18 Gbps across a 128-bit bus interface, and 288 GB/s of bandwidth. The GPU also has 32 MB of L2 cache, which is an 8x increase over the GeForce RTX 3060 Ti.
- Microsoft and Japanese cloud gaming provider Ubitus signs a 10-year agreement deal
- Google Pixel Fold and Pixel 7a details leak ahead of the Google I/O 2023