NVIDIA’s GeForce RTX 4090 is not yet available for sale, and news of an enhanced version of the flagship graphics card, the RTX 4090 Ti, has leaked. According to the information disclosed by reliable whistleblower @XpeaGPU, NVIDIA GeForce RTX 4090 Ti uses the best AD102 GPU dies. This should come as no surprise, as the same thing happened with the RTX 3090 Ti.
Visit the purchase page:
Summary of Jingdong NVIDIA series products
The NVIDIA GeForce RTX 4090 Ti is said to be a “chicken blood” configuration with all 144 SMs enabled for a total of 18432 CUDA cores. The GPU will come with 96 MB of L2 cache and a total of 224 ROPs, which is insane.
The card will retain the TSMC 4N process node and offer a nice clock speed boost, the card is rated at 2.75 GHz (default) and can reach boost clocks of 2.95 or even 3 GHz in typical gaming workloads. The default clock has been increased by +190 MHz.
In terms of memory, the GeForce RTX 4090 Ti will have 24 GB of GDDR6X capacity, which will likely be available at a faster 24 Gbps over a 384-bit bus interface. This will provide up to 1.152 TB/s of bandwidth.
And all these boosted specs will also lead to higher power consumption, with the flagship expected to run at a TBP of around 600W. The card is said to have a TGP of 475W, which is a 25W increase over the RTX 4090, but custom variants could push that up into the 600W+ range again.
The NVIDIA GeForce RTX 4090 is a very efficient graphics card that can deliver the same performance at 70% less than its power budget. If the 4090 Ti does use a binned chip, that might explain the lower wattage numbers, as NVIDIA can further optimize the voltage.
The RTX 4090 Ti is said to perform 10-20% better than the RTX 4090, so it will definitely match or even exceed the 2x performance figures of the RTX 3090 Ti, which would be really impressive. However, cards of this nature won’t be coming out anytime soon.