The RTX 3090 Ti was unlucky and was tragically skipped because NVIDIA was secretive and the outside world did not know when this card king would appear. It seems that the ampere architecture has indeed come to an end.
It is believed that within the NV, the motivation to actively prepare for the RTX 40 Series is more powerful than the power to solve the troubles of the RTX 3090 Ti.
A few days ago, foreign hardware blogger Graphicly Challenged gave a price forecast for RTX 40 series graphics cards, compared with the previous statement that RTX 4090 will sell for $2999 and RTX 4050 will sell for $279, and made corresponding adjustments, because the graphics card market is volatile and supply is improving.
Its latest video points out that the RTX 4090 is expected to be officially priced at $1899, of course, even so it is $400 more expensive than the RTX 3090, according to the NV "exchange rate" of about 1:8, the retail price of the Bank of China is likely to exceed 15,000.
In terms of timing, GC concluded that it would be released in September and listed in October.
As for the specifications, previous reports said that the RTX 40 series GPU is Ada Lovelace, 5nm process, RTX 4090 corresponding to the AD102 large core, there will be as many as 12 GPC (graphics processing cluster), 72 TPC (texture processing cluster), 144 SM (streaming multiprocessor), and each SM continues to 128 stream processors (CUDA core), then the overall number of up to 18432 stream processors, Compared with the current AMP architecture GA102 core of 10752 cores, an increase of 71%, the overall performance is doubled.
The AD102 can travel up to 2.5GHz and floating-point performance up to 90TFLOPS, a 152% increase compared to the RTX 3090 and a 125% increase over the RTX 3090 Ti.
![NVIDIA MX 550 Graphics Card Exposure: 15% performance based on ampere architecture[fig]](data:image/gif;base64,R0lGODlhAQABAIAAAP///wAAACwAAAAAAQABAAACAkQBADs=)