NVIDIA’s upcoming GeForce RTX 2060 revival with 12 GB of GDDR6 memory will have the same CUDA core count as the GeForce RTX 2060 SUPER. That’s according to multiple sources with VideoCardz, all of whom have relayed new and similar specifications for the Turing-based graphics card. The GeForce RTX 2060 (12 GB) is said to feature 2,176 cores and a 1,650 MHz boost clock just like the SUPER model but differ in a few areas such as memory bandwidth and thermal design power.
From VideoCardz:
[…] 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 will reportedly launch the GeForce RTX 2060 (12 GB) on December 7, 2021. The original GeForce RTX 2060 was released on January 15, 2019, nearly three years ago.
Source: VideoCardz