The overlocking team over at Brazilian publication Teclab has successfully transplanted memory chips from two RTX 2080 Super graphics cards into an RTX 2080 Ti to make what would be the equivalent to an RTX 2080 Ti Super.
The RTX 2080 Ti is equipped with 11GB of GDDR6 memory clocked at 1,750 MHz (14,000 MHz effective). On the other hand, the RTX 2080 Super has 8GB of GDDR6 memory rated for 2,000 MHz (16,000 MHz); however, it runs at 1,937 MHz (15,496 MHz effective). Basically, we're looking at a 10.7% difference in memory speeds between the two Turing-powered graphics cards.
There's memory disparity between the RTX 2080 Ti and RTX 2080 Super. The RTX 2080 Ti uses 11 memory chips, while the RTX 2080 Super only has eight. This is why Techlab needed to dismantle two RTX 2080 Super graphics cards to make its experiment work instead of just one. The team didn't use reference models either, but rather offerings from Galax that total up to an eye-watering $3,400.
Even more impressive is the surgical procedure used to extract the necessary memory chips from the two RTX 2080 Super cards, which required reballing them one by one before implanting them into the RTX 2080 Ti.
Teclab noted that the RTX 2080 Ti Super booted up just fine with the RTX 2080 Super's memory. The graphics card's vBIOS accepted the new memory with open arms and ran it at 1,750 MHz, so no BIOS modding was required. In the end, the team was able to push the memory to 2,150 MHz (17,200 MHz effective), which represents a 22.9% and 10.7% increase over the RTX 2080 Ti's and RTX 2080 Super's default memory, respectively.
Unfortunately, Teclab didn't thoroughly test its "RTX 2080 Ti Super" to see how it performs with faster memory. The team only provided a Superposition run, where the graphics card put up a score of 11,460 points with the 1080p Extreme preset. A stock RTX 2080 Ti typically scores between 8,600 and 9,200 points.
So there you have it, folks. A Frankenstein-like interpretation of what an RTX 2080 Ti Super would look like -- that is unless Nvidia actually does decide to make the GPU but enable more CUDA cores in addition to incorporating that faster memory.