Introduction

Zotac GeForce RTX 4070 AMP Airo is the company’s top-of-the-line custom design based on the RTX 4070 Ada. It gives you the company’s highest factory overclock for this GPU, its most elaborate VRM solution, and is among the handful of custom RTX 4070 cards to come with a 12VHPWR connector. The AMP Airo is also the company’s most premium-looking RTX 4070 product, and is sure to look like it’s from a segment above, with eye-catching RGB LED lighting and a large triple-slot design. The GeForce RTX 4070 is designed to offer maxed out gaming with ray tracing at 1440p resolution, as well as high refresh-rate e-sports gaming. It’s also capable of 4K Ultra HD, if you dial down your game’s settings, or let GeForce Experience to choose the best ones. You can also take advantage of DLSS and DLAA, as well as the latest DLSS 3 Frame Generation.

The GeForce RTX 4070 Ada is based on the same 5 nm AD104 silicon as the RTX 4070 Ti, but is slightly cut down. The card comes with 46 out of 60 streaming multiprocessors (SM) enabled, which results in 5,888 CUDA cores, 46 RT cores, 184 Tensor cores, and 184 TMUs. The GPU’s ROP count has been reduced to 64 from 80 on the RTX 4070 Ti, as has the on-die L2 cache, to 36 MB from 48 MB on the Ti. Interestingly, the shader count is identical to that of the popular RTX 3070, which it succeeds. The memory sub-system, interestingly, is unchanged from the RTX 4070 Ti—you get 12 GB of 21 Gbps GDDR6X memory across a 192-bit memory interface. Generationally, the memory bus width is narrower, but the memory size and speed have both been increased by over 50%. NVIDIA has re-architected the memory sub-system, with large on-die caches playing a big role in reducing the round-trips to the video memory, allowing NVIDIA to narrow the bus width. The biggest difference between the RTX 4070 and the RTX 4070 Ti is the 30% lower typical power of just 200 W, which has enabled board partners to opt for a single 8-pin PCIe power connector. The Zotac AMP Airo, however, uses the more advanced 16-pin 12VHPWR.

The new GeForce Ada Lovelace graphics architecture debuts the third generation of RTX, the pioneering gaming graphics innovation by NVIDIA that combines real-time ray traced elements with conventional raster graphics, to significantly increase realism. Even this bit of ray tracing requires an enormous amount of compute power, and so the company innovated fixed-function hardware in the form of RT cores, and uses AI deep-learning for de-noising—which is where the Tensor cores step in. The new Ada Lovelace CUDA core, in addition to generational improvements in IPC and math formats, supports shader execution reordering. The 3rd Gen RT core, in addition to generational ray intersection performance improvements, introduces new features such as Displaced Micro-meshes. DLSS 3 is perhaps the biggest innovation with the RTX 40-series. Entire alternate frames are generated entirely using AI, without involving the graphics rendering pipeline, nearly doubling performance, all thanks to the new optical flow accelerator.

The Zotac GeForce RTX 4070 AMP Airo features the same Ice Storm 2.0 triple-slot, triple-fan cooling solution that the company uses with its RTX 4070 Ti AMP series graphics cards. The cooler is designed for 300 W-class GPUs from a segment above. A large aluminium fin-stack heatsink is ventilated by three large fans with a high degree of airflow optimization and fan tuning. The 30.7 cm card is longer than the PCB underneath, so much of the airflow from the third fan passes through the cooler, and out vents on the backplate. The RTX 4070 AMP Airo features Zotac’s Spectra 2.0 RGB lighting, in the form of a large RGB LED diffuser along the top of the card that resembles a neon sign. The Zotac AMP Airo comes with factory overclocked speeds of up to 2535 MHz boost compared to 2475 MHz reference, while leaving the memory speed untouched at 21 Gbps. While the default power limit sticks to NVIDIA reference settings of 200 W, the manual adjustment range goes up to 240 W. Zotac is pricing the RTX 4070 AMP Airo at $640, a not-unreasonable $40 premium over the NVIDIA MSRP.