Nvidia has obtained a good quantity of criticism for its energy hungry high-end GeForce RTX 40-series graphics playing cards based mostly on the Ada Lovelace structure. In line with famend {hardware} leaker @kopite7kimi, Nvidia is now seeking to make its mainstream GeForce RTX 4060 Ti half much more energy environment friendly.
As ever with leaks, take the information with a pinch till actual world benchmarks and checks may be undertaken.
In line with kopite7kimi, the GeForce RTX 4060 Ti could have a thermal graphics energy of as much as 160W as an alternative of 220W reported initially. In the meantime, normal specs of the product are set to stay usually the identical: the board might be powered by the AD106 graphics processing unit with 4352 CUDA cores and accompanied by 8GB of 18 Gbps GDDR6 reminiscence linked utilizing a 128-bit interface.
Proper now, it’s unclear how the brand new TGP impacts GPU frequencies and efficiency of the GeForce RTX 4060 Ti and AD106 processor. With 4352 CUDA cores, the GeForce RTX 4060 Ti is already considerably behind rumored specs of the GeForce RTX 4070, which allegedly has 5888 CUDA cores. If AD106’s GPU clocks are dropped considerably from these deliberate initially, efficiency hole between GeForce RTX 4070 and RTX 4060 Ti might be important.
| GPU | FP32 CUDA Cores | Reminiscence Configuration | TBP | |
| GeForce RTX 4090 | AD102 | 16384 | 24GB 384-bit 21 GT/s GDDR6X | 450W |
| GeForce RTX 4080 | AD103 | 9728 | 16GB 256-bit 22.4 GT/s GDDR6X | 320W |
| GeForce RTX 4070 Ti | AD104 | 7680 | 12GB 192-bit 21 GT/s GDDR6X | 285W |
| GeForce RTX 4070 | AD104 | ?5888? | 12GB 192-bit 21 GT/s GDDR6X | ?250W? |
| GeForce RTX 4060 Ti | AD106 | ?4352? | 8GB 128-bit 18 GT/s GDDR6 | ?160W? |
With 8GB of 128-bit GDDR6 reminiscence, Nvidia’s GeForce RTX 4060 Ti might provide a reminiscence bandwidth that’s 43% decrease in comparison with that of the GeForce RTX 4070, so the hole between two merchandise in reminiscence bandwidth-dependent workloads (e.g., in excessive resolutions and/or with antialiasing enabled) could also be big. In the meantime, the brand new product may even characteristic a 36% decrease reminiscence bandwidth than its direct predecessor, the GeForce RTX 3060 Ti with GDDR6 reminiscence. In fact, we’d anticipate 32MB of L2 cache to considerably cut back bandwidth limitations, however solely checks will reveal whether or not that is the case.
In the meantime, carrying solely 8GB of reminiscence is one other peculiarity that can be seen as a limitation. We already felt the 8GB of reminiscence on the GeForce RTX 3060 Ti, 3070, and 3070 Ti was changing into a limiting issue and people are outgoing merchandise launched in 2020 – 2021. Regardless of all these elements, the GeForce RTX 4060 Ti remains to be more likely to be part of the ranks of the greatest graphics playing cards as it is going to simply outperform its predecessor.
With a 160W TGP, the GeForce RTX 4060 Ti might place itself as a viable graphics resolution for small kind issue gaming PCs. The board is rumored to characteristic a really brief reference design, so anticipate Nvidia’s companions to supply dual-slot boards for Mini-ITX machines and even perhaps single-slot variants for skinny PCs.
Needless to say we’re speaking about specs leaked by an unofficial supply, so take them with a pinch of salt, although it’s believable that Nvidia determined to construct an energy-efficient but highly effective GPU to higher compete for compact gaming PCs.