NVIDIA’s upcoming mainstream graphics card, the GeForce RTX 4060 Ti, has revealed its expected clock speeds and compute performance. Videocardz’s most recent compute figures are based on recently rumoured specifications and clock speeds. TFC Fantasy, TechpowerUp’s GPU database editor, reported the clock frequencies of various models, while Kopite7kimi posted the specifications for the RTX 4060 Ti graphics card.
According to reports, the NVIDIA GeForce RTX 4060 Ti will have a base clock of 2310 MHz and a boost clock of 2535 MHz, with premium models capable of clocking up to 2685 MHz.
The GeForce RTX 4060 Ti is expected to use the AD106-350-A1 GPU core, a scaled-down version of the full AD106 graphics chip, with 34 SMs or 4352 CUDA cores, an 8 GB GDDR6 memory running at 18 Gbps across a 128-bit bus interface, and 288 GB/s of bandwidth. The GPU also has 32 MB of L2 cache, which is an 8x increase over the GeForce RTX 3060 Ti.
According to leaked PCB images, the RTX 4060 Ti, like the RTX 4070, will continue to use the PCIe Gen5 12VHPWR connector because NVIDIA wants to standardise it across the entire lineup. In addition, the graphics card will have compact PCB designs in both reference and non-reference flavours. The card is expected to have a TGP of 160W, which is 20% less than its predecessor, the RTX 3060 Ti.
Using the rumoured “reference” boost frequency as a guide, the NVIDIA GeForce RTX 4060 Ti should provide around 22 TFLOPs of compute performance, with AIB models pushing it closer to 24 TFLOPs.
Based on the numbers, it appears that the NVIDIA GeForce RTX 4060 Ti graphics card will perform similarly to the GeForce RTX 3070 Ti. The 3070 Ti debuted at $599 US, so the 4060 Ti would have to be priced around $399 US to be a worthy successor to the 3060 Ti, which debuted at the same price. The main issue is that, while the card performs well at 1080p, higher resolutions would be difficult due to its 128-bit bus interface and reliance on slower G6 memory rather than G6X memory.
Also Read:
