NVIDIA RTX 2060 12GB, more than a just memory upgrade
We received new information on the upcoming RTX 2060 12GB graphics cards.
As it turns out, the soon-to-release ‘upgraded’ RTX 2060 model is said to feature more than 1920 CUDA cores. The card that is now known as RTX 2060 12GB is now expected to use 2176 CUDA cores, which is the same number as RTX 2060 SUPER. Interestingly, the new SKU is to have a higher default TDP of 184W (compared to SUPER’s 175W), which makes this new announcement even more strange. On paper, the card is expected to be just about the same as 2060 SUPER except for the memory bandwidth: the 2060 SUPER variant has a 256-bit bus while the 12GB SKU is 192-bit.
Obviously, we were quite surprised by this rumor, but we have since confirmed this information with as many as three sources. They have all received the same specifications: 2176 CUDA cores, 12GB GDDR6 14Gbps memory across a 192-bit bus, and 184W TDP. As for the boost clock, two sources claim it is a 1650 MHz boost by default with factory-overclocked variants going into 1690 Mhz space.
NVIDIA RTX 2060 12GB is now set to launch on December 7th as a cheaper alternative to RTX 3060 12GB (hopefully with better availability). It is worth noting that at launch the RTX 3060 12GB was around 8% faster than RTX 2060 SUPER. The 2060 12GB, considering it has nearly identical specs, might perform just about the same. The features that will be missing on the Turing model though are PCIe Gen4 and ResizableBAR support. The card will also have lower raytracing performance.
NVIDIA GeForce RTX x60 Series | |||||
---|---|---|---|---|---|
VideoCardz.com | GeForce RTX 2060 SUPER | GeForce RTX 2060 12GB | GeForce RTX 2060 6GB | GeForce RTX 3060 Ti | GeForce RTX 3060 |
Picture | ![]() | ![]() | ![]() | ![]() | ![]() |
Architecture | NVIDIA Turing | NVIDIA Turing | NVIDIA Turing | NVIDIA Ampere | NVIDIA Ampere |
Board | PG150 | PG161 | PG160 | PG190/PG142 | PG190 |
GPU | 12nm TU106-410 | 12nm TU106 | 12nm TU106-300 | 8nm GA104-200 | 8nm GA106-300 |
Boost Clock | |||||
CUDA : RT : Tensor | |||||
Memory | |||||
Memory Clock | |||||
Memory Bus | |||||
Memory Bandwidth | |||||
TGP/TBP | |||||
MSRP | TBC | ||||
Release Date | July 9th, 2019 | December 7th, 2021 | January 14, 2019 | December 2nd, 2020 | Late February 2021 |