Introduction

We have with us the Zotac GeForce RTX 4070 Ti SUPER Trinity Black. NVIDIA today rolled out the GeForce RTX 4070 Ti SUPER, the second in its three-part RTX 40 SUPER series mid lifecycle refresh for its current generation. Modeled along the lines of its RTX 20-series SUPER, this refresh focuses on the upper end of the product stack, and brings more performance at existing price points. The RTX 4070 Ti SUPER replaces the RTX 4070 Ti from its $800 price point, which will be phased out from the lineup. The new RTX 4070 Ti SUPER continues to be recommended by NVIDIA for maxed out 1440p gaming, although we’ve found even the RTX 4070 Ti to be capable of 4K Ultra HD gameplay at reasonably high settings. You now have four SKUs in the RTX 4070 series, which should make one wonder who the RTX 4070 Ti SUPER is really for. The popular 1440p or 2K is a good middle of the market resolution between Full HD 1080p and 4K, and 1440p monitors with 144 Hz or 165 Hz refresh rates are fairly affordable. The RTX 4070 Ti SUPER should appeal to this class of gamer, as it should offer sufficient frame rates to keep up.

The SUPER moniker denotes more performance at existing price points, through uplifts in specs, although no new features are introduced. This is still the same 5 nm Ada Lovelace architecture driving these cards. Given that NVIDIA had maxed out the AD104 silicon to create the RTX 4070 Ti, it now taps into the larger AD103 chip also used to power the RTX 4080. The switch to the larger silicon also brings the biggest change for the RTX 4070 Ti SUPER over its predecessor—memory. With a 256-bit wide memory interface at its disposal, compared to the 192-bit of the AD104, the new RTX 4070 Ti SUPER gets 16 GB of memory. Besides the 4 GB of extra memory, it’s the 33% extra memory bandwidth that’s the main story here, and this review will answer the question that’s been on everyone’s minds since the RTX 4070 and RTX 4070 Ti launch—whether the AD104 silicon with its 192-bit memory bus is starved for memory bandwidth.

NVIDIA carved the RTX 4070 Ti SUPER out of the AD103 silicon by enabling 66 out of 80 streaming multiprocessors (SM) present on the silicon. This is six more SM than the RTX 4070 Ti, or a 10% increase in CUDA cores; but 10 fewer SM than the RTX 4080. The upcoming RTX 4080 SUPER maxes out this silicon, enabling all 80 SM. With 66 available SM, the RTX 4070 Ti SUPER gets 8,448 CUDA cores on tap, along with 264 Tensor cores, 66 RT cores, and 264 TMUs. NVIDIA has enabled 96 out of 112 ROPs present on the AD103, which is fewer than those on the RTX 4080, but still a 20% gain over the 80 ROPs of the original RTX 4070 Ti. The on die L2 cache size is reduced to 48 MB compared to the 64 MB present on the silicon, which has been maxed out by the RTX 4080. The GPU frequency is set to 2610 MHz boost, and the memory ticks at 21 Gbps, which again, is lower compared to the 22.5 Gbps of the RTX 4080, and 23 Gbps of the RTX 4080 SUPER; but produces 672 GB/s of memory bandwidth that’s 33% higher than the 504 GB/s of the RTX 4070 Ti.

The new Ada Lovelace graphics architecture debuts generational gains in performance and energy efficiency, thanks to the new 5 nm EUV foundry node. The new generation CUDA core, besides the usual IPC gains, now supports shader execution reordering, which benefits ray tracing workloads. The new 3rd generation RT core improves ray intersection performance, as well as introduces support for displaced micro-meshes, a feature that should increase the geometric complexity of ray traced objects. The new optical flow accelerator is a required hardware resource for DLSS 3 Frame Generation to work.

The new Zotac GeForce RTX 4070 Ti SUPER Trinity Black is the company’s most affordable RTX 4070 Ti SUPER product, coming in at the $800 NVIDIA MSRP. It features the IceStorm 2 triple-slot cooling solution that features elements of the company’s new AIRO design language that streamlines airflow from the fans across the heatsink, and from a design standpoint, features more curvy, futuristic contours compared to some of the boxy-looking custom designs out there. There’s some RGB lighting to be had, too, in the form of illuminated logos on the top of the card, and at the backplate. The card sticks with NVIDIA reference clock speeds of 2610 MHz boost, and 21 Gbps (GDDR6X effective) memory.