Introduction

PNY GeForce RTX 4060 Ti XLR8 is a premium custom-design RTX 4060 Ti graphics card by the company that has established itself as a major player in the gaming graphics space, from its professional graphics and memory solutions roots. The XLR8 (pronounced “accelerate”) features a large and illuminated cooling solution that makes the card look like it’s from a segment above. While positioned above the $399 MSRP for the RTX 4060 Ti, this particular card is not factory-overclocked. PNY offers an identical-looking card with factory OC, called the RTX 4060 Ti XLR8 OC. You get the same cooling and power-delivery regardless, so you can try your hand in some manual overclocking.

The GeForce RTX 4060 Ti Ada is a mid-range graphics card intended to succeed the RTX 3060 Ti, and designed for 1080p AAA gaming with maxed out settings, including ray tracing. You can also game at 1440p, if you know your way around your game’s graphics settings; or you can just get GeForce Experience to find the best ones. Since it’s based on the latest Ada Lovelace graphics architecture and built on the 5 nm process, you get the benefit of the most energy-efficiency in this product generation, as well as exclusive features, such as DLSS 3—a path-breaking new tech that draws entire alternate frames using AI, without involving the graphics rendering machinery, so you effectively get double the frame-rates in games optimized for it. DLSS 3 is particularly relevant in this segment to enable usage of ray tracing, consistent high FPS, or both.

The GeForce RTX 40-series Ada debuts the third generation of RTX, NVIDIA’s ground-breaking technology that ups realism in games by combining real-time ray traced elements with conventional raster 3D graphics. Even this bit of ray tracing requires enormous compute power, and so the company created dedicated hardware inside the GPU that takes care of these workloads. Ada debuts the 3rd generation RT core with a generational uplift in ray tracing intersection performance; and 4th generation Tensor cores, which accelerate AI deep-learning neural nets, by tapping into even newer capabilities. The faster Ada CUDA core, plus higher GPU clock-speeds, and a completely redesigned memory sub-system with larger on-die caches.

The GeForce RTX 4060 Ti debuts the 5 nm AD106 silicon to the desktop segment. It is carved out of this chip by enabling 34 out of 36 SM (streaming multiprocessors), which works out to 4,352 CUDA cores, 34 RT cores, 136 Tensor cores, 48 ROPs, and 136 TMUs. The RTX 4060 Ti being reviewed today comes with 8 GB of GDDR6 memory across a 128-bit memory interface. This is generationally narrowed compared to the 256-bit interface of the RTX 3060 Ti, but NVIDIA has redesigned the memory sub-system with Ada. NVIDIA has deployed an 8-times larger on-die last-level cache of 32 MB (compared to 4 MB on the GA104 silicon powering the RTX 3060 Ti), which the company claims reduces the load on the video memory for most frequent data-access, allowing it to narrow the memory bus.

The PNY RTX 4060 Ti XLR8 features the company’s Verto EPIC-X RGB cooling solution. This dual-slot cooler uses a large aluminium fin-stack heatsink that’s ventilated by three fans. There’s plenty of RGB LED illumination to be had. Given that the TGP of the RTX 4060 Ti at reference speeds is rated at just 160 W, the card makes do with a single 8-pin PCIe power connector. It doesn’t really need the 16-pin 12VHPWR connector that the NVIDIA Founders Edition comes with. PNY is pricing the RTX 4060 Ti XLR8 at a premium price of $450, which is why it missed out on reviews yesterday (May 23). We did present our review of its more cost-effective sibling, the RTX 4060 Ti Verto.