NVIDIA RTX 4060 Ti may offer a remarkable computing performance of 22 TFLOPs

Currently, Nvidia is busy with the upcoming new Ada Lovelace architecture GPU. According to previously leaked information, the GeForce RTX 4070 will arrive next month, while the RTX 4060 Ti and RTX 4060 are also ready to be released in the second quarter of this year. The Founders Edition graphics card, which was exposed some time ago, indicates that the new products are in preparation, but at present, there is still relatively little information available.

Recently, T4C Fantasy, the database editor and maintainer for TechPowerUp, received new information regarding the GeForce RTX 4060 Ti. It is reported that its base clock is 2310MHz, and its boost clock is 2535MHz, with some non-public versions increasing the clock to 2685MHz.

In other words, the base clock of the GeForce RTX 4060 Ti is the same as that of the RTX 4070 Ti, but the boost clock is 75MHz lower. Based on this leaked information, it can be inferred that the computational performance of the GeForce RTX 4060 Ti will reach 22.1 TFLOP, roughly half that of the RTX 4070 Ti, which is about 40.1 TFLOP.

As previously mentioned, the GeForce RTX 4060 Ti is equipped with the AD106-350 GPU, with 4352 CUDA cores, 8GB of GDDR6 memory, a 128-bit memory interface, and a memory clock speed of 21 Gbps, with a total card power consumption of 160W. The GeForce RTX 4060 is equipped with the AD107-400 GPU, with 3072 CUDA cores, the same memory specifications, and a total card power consumption reduced to 115W.

It is rumored that both the RTX 4060 Ti and RTX 4060 will use PCIe 4.0 x8 interfaces, and both may be released in May of this year.