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.
Short 10-Minute Video Comparing 10x RTX 4070 Ti Super
Our goal with the videos is to create short summaries, not go into all the details and test results, which can be found in our written reviews.
NVIDIA GeForce RTX 4070 Ti Super Market Segment Analysis
Price
Cores
ROPs
Core Clock
Boost Clock
Memory Clock
GPU
Transistors
Memory
RTX 3070 Ti
$350
6144
96
1575 MHz
1770 MHz
1188 MHz
GA104
17400M
8 GB, GDDR6X, 256-bit
RX 6800
$450
3840
96
1815 MHz
2105 MHz
2000 MHz
Navi 21
26800M
16 GB, GDDR6, 256-bit
RX 7700 XT
$430
3456
96
2171 MHz
2544 MHz
2250 MHz
Navi 32
26500M
12 GB, GDDR6, 192-bit
RX 6800 XT
$500
4608
128
2015 MHz
2250 MHz
2000 MHz
Navi 21
26800M
16 GB, GDDR6, 256-bit
RTX 3080
$450
8704
96
1440 MHz
1710 MHz
1188 MHz
GA102
28000M
10 GB, GDDR6X, 320-bit
RTX 4070
$540
5888
64
1920 MHz
2475 MHz
1313 MHz
AD104
35800M
12 GB, GDDR6X, 192-bit
RX 7800 XT
$500
3840
96
2124 MHz
2430 MHz
2425 MHz
Navi 32
28100M
16 GB, GDDR6, 256-bit
RX 6900 XT
$650
5120
128
2015 MHz
2250 MHz
2000 MHz
Navi 21
26800M
16 GB, GDDR6, 256-bit
RX 6950 XT
$630
5120
128
2100 MHz
2310 MHz
2250 MHz
Navi 21
26800M
16 GB, GDDR6, 256-bit
RTX 3090
$800
10496
112
1395 MHz
1695 MHz
1219 MHz
GA102
28000M
24 GB, GDDR6X, 384-bit
RTX 4070 Super
$600
7168
80
1980 MHz
2475 MHz
1313 MHz
AD104
35800M
12 GB, GDDR6X, 192-bit
RTX 4070 Ti
$750
7680
80
2310 MHz
2610 MHz
1313 MHz
AD104
35800M
12 GB, GDDR6X, 192-bit
RTX 4070 Ti Super
$800
8448
112
2340 MHz
2610 MHz
1313 MHz
AD103
45900M
16 GB, GDDR6X, 256-bit
Zotac RTX 4070 Ti Super Trinity
$800
8448
112
2340 MHz
2610 MHz
1313 MHz
AD103
45900M
16 GB, GDDR6X, 256-bit
RX 7900 XT
$710
5376
192
2000 MHz
2400 MHz
2500 MHz
Navi 31
57700M
20 GB, GDDR6, 320-bit
RTX 3090 Ti
$1050
10752
112
1560 MHz
1950 MHz
1313 MHz
GA102
28000M
24 GB, GDDR6X, 384-bit
RTX 4080
$1200
9728
112
2205 MHz
2505 MHz
1400 MHz
AD103
45900M
16 GB, GDDR6X, 256-bit
RTX 4080 Super
$1000
10240
112
2295 MHz
2550 MHz
1400 MHz
AD103
45900M
16 GB, GDDR6X, 256-bit
RX 7900 XTX
$970
6144
192
2300 MHz
2500 MHz
2500 MHz
Navi 31
57700M
24 GB, GDDR6, 384-bit
RTX 4090
$2000
16384
176
2235 MHz
2520 MHz
1313 MHz
AD102
76300M
24 GB, GDDR6X, 384-bit
Architecture
The Ada graphics architecture heralds the third generation of the NVIDIA RTX technology, an effort toward increasing the realism of game visuals by leveraging real-time ray tracing, without the enormous amount of compute power required to draw purely ray-traced 3D graphics. This is done by blending conventional raster graphics with ray traced elements such as reflections, lighting, and global illumination, to name a few. The 3rd generation of RTX introduces the new higher IPC "Ada" CUDA core, 3rd generation RT core, 4th generation Tensor core, and the new Optical Flow Processor, a component that plays a key role in generating new frames without involving the GPU's main graphics rendering pipeline. The GeForce Ada graphics architecture driving the RTX 4070 Ti SUPER leverages the TSMC 5 nm EUV foundry process to increase transistor counts.
The GeForce RTX 4070 Ti SUPER gets a significant memory sub-system uplift over the original RTX 4070 Ti, besides an increase in shaders and other on-die components. Since NVIDIA maxed out the AD104 to create the RTX 4070 Ti, the only way it could go about creating the RTX 4070 Ti SUPER is by tapping into the larger AD103 that powers the RTX 4080 and the upcoming RTX 4080 SUPER. The biggest perks of the switch to AD103 is its wider 256-bit memory bus, which allowed NVIDIA to increase the memory from 12 GB to 16 GB.
The AD103 die is built on the 5 nm EUV foundry process, with a die size of 379 mm² and 45.9 billion transistors. The chip features a PCI-Express 4.0 x16 host interface along with support for PCI resizable BAR; and its 256-bit wide GDDR6X memory interface. The GigaThread Engine serves as the main workflow controller for the GPU, dispatching work among the GPU's 7 graphics processing clusters (GPCs). Each GPC shares a Raster Engine and render backends among six texture processing clusters (TPCs), the indivisible subunit of the GPU. Each of these has two Streaming Multiprocessors (SM), and a Polymorph unit. Each SM contains 128 CUDA cores across four partitions. Half of these CUDA cores are pure-FP32; while the other half is capable of FP32 or INT32. The SM retains concurrent FP32+INT32 math processing capability. The SM also contains a 3rd generation RT core, four 4th generation Tensor cores, some cache memory, and four TMUs. One of the seven GPCs on the AD103 physically only has four TPCs.
With a total of 40 TPCs, or 80 SM, AD103 physically features 10,240 CUDA cores, 320 Tensor cores, 80 RT cores, and 320 TMUs; along with 64 MB of on-die L2 cache, and 112 ROPs. NVIDIA carved the RTX 4070 Ti SUPER out of the AD103 by enabling 66 out of 80 SM, 48 MB out of the 64 MB of L2 cache present; and 96 ROPs out of the 112 present. This results in 8,448 CUDA cores, 264 Tensor cores, 66 RT cores, 264 TMUs, 96 ROPs, and 48 MB of L2 cache. NVIDIA also disabled a few NVDEC units, giving this the same exact video acceleration configuration as the RTX 4070 Ti, with two NVENC and one NVDEC units. The 256-bit memory interface drives 16 GB of memory, however the memory runs at 21 Gbps, compared to the 22.5 Gbps of the RTX 4080, and 23 Gbps of the upcoming RTX 4080 SUPER. Even with 21 Gbps, the memory bandwidth on tap is an impressive 672 GB/s, a 33% increase over that of the original RTX 4070 Ti.
3rd Gen RT Core and Ray Tracing
The 3rd generation RT core accelerates the most math-intensive aspects of real-time ray tracing, including BVH traversal. Displaced micro-mesh engine is a revolutionary feature introduced with the new 3rd generation RT core. Just as mesh shaders and tessellation have had a profound impact on improving performance with complex raster geometry, allowing game developers to significantly increase geometric complexity; DMMs is a method to reduce the complexity of the bounding-volume hierarchy (BVH) data-structure, which is used to determine where a ray hits geometry. Previously, the BVH had to capture even the smallest details to properly determine the intersection point. Ada's ray tracing architecture also receives a major performance uplift from Shader Execution Reordering (SER), a software-defined feature that requires awareness from game-engines, to help the GPU reorganize and optimize worker threads associated with ray tracing.
The BVH now needn't have data for every single triangle on an object, but can represent objects with complex geometry as a coarse mesh of base triangles, which greatly simplifies the BVH data structure. A simpler BVH means less memory consumed and helps to greatly reduce ray tracing CPU load, because the CPU only has to generate a smaller structure. With older "Ampere" and "Turing" RT cores, each triangle on an object had to be sampled at high overhead, so the RT core could precisely calculate ray intersection for each triangle. With Ada, the simpler BVH, plus the displacement maps can be sent to the RT core, which is now able to figure out the exact hit point on its own. NVIDIA has seen 11:1 to 28:1 compression in total triangle counts. This reduces BVH compile times by 7.6x to over 15x, in comparison to the older RT core; and reducing its storage footprint by anywhere between 6.5 to 20 times. DMMs could reduce disk- and memory bandwidth utilization, utilization of the PCIe bus, as well as reduce CPU utilization. NVIDIA worked with Simplygon and Adobe to add DMM support for their tool chains.
Opacity Micro Meshes
Opacity Micro Meshes (OMM) is a new feature introduced with Ada to improve rasterization performance, particularly with objects that have alpha (transparency data). Most low-priority objects in a 3D scene, such as leaves on a tree, are essentially rectangles with textures on the leaves where the transparency (alpha) creates the shape of the leaf. RT cores have a hard time intersecting rays with such objects, because they're not really in the shape that they appear (they're really just rectangles with textures that give you the illusion of shape). Previous-generation RT cores had to have multiple interactions with the rendering stage to figure out the shape of a transparent object, because they couldn't test for alpha by themselves.
This has been solved by using OMMs. Just as DMMs simplify geometry by creating meshes of micro-triangles; OMMs create meshes of rectangular textures that align with parts of the texture that aren't alpha, so the RT core has a better understanding of the geometry of the object, and can correctly calculate ray intersections. This has a significant performance impact on shading performance in non-RT applications, too. Practical applications of OMMs aren't just low-priority objects such as vegetation, but also smoke-sprites and localized fog. Traditionally there was a lot of overdraw for such effects, because they layered multiple textures on top of each other, that all had to be fully processed by the shaders. Now only the non-opaque pixels get executed—OMMs provide a 30 percent speedup with graphics buffer fill-rates, and a 10 percent impact on frame-rates.
DLSS 3 Frame Generation
DLSS 3 introduces a revolutionary new feature that promises a doubling in frame-rate at comparable quality, it's called AI frame-generation. Building on DLSS 2 and its AI super-resolution (scaling up a lower-resolution frame to native resolution with minimal quality loss); DLSS 3 can generate entire frames simply using AI, without involving the graphics rendering pipeline, it's also possible to enable frame generation at native resolution without upscaling. Later in the article, we will show you DLSS 3 in action.
Every alternating frame with DLSS 3 is hence AI-generated, without being a replica of the previous rendered frame. This is possible only on the Ada graphics architecture, because of a hardware component called the optical flow accelerator (OFA), which assists in predicting what the next frame could look like, by creating what NVIDIA calls an optical flow-field. OFA ensures that the DLSS 3 algorithm isn't confused by static objects in a rapidly-changing 3D scene (such as a race sim). The process heavily relies on the performance uplift introduced by the FP8 math format of the 4th generation Tensor core. A third key ingredient of DLSS 3 is Reflex. By reducing the rendering queue to zero, Reflex plays a vital role in ensuring that latency with DLSS 3 enabled is at an acceptable level. A combination of OFA and the 4th Gen Tensor core is why the Ada architecture is required to use DLSS 3, and why it won't work on older architectures.
Packaging
The Card
Zotac RTX 4070 Ti Super Trinity uses a clean color theme with a rounded cooler design. On the back you get a metal backplate with a cutout for air to flow through.
Dimensions of the card are 31.0 x 12.0 cm, and it weighs 1084 g.
Installation requires three slots in your system. We measured the card's width to be 60 mm.
Display connectivity includes three standard DisplayPort 1.4a ports and one HDMI 2.1a (same as Ampere and same as non-Super Ada).
NVIDIA introduced the concept of dual NVDEC and NVENC Codecs with the Ada Lovelace architecture. This means there are two independent sets of hardware-accelerators; so you can encode and decode two streams of video in parallel or one stream at double the FPS rate. While the RTX 4070 Ti features dual units, the RTX 4070 Super and RTX 4070 come with only one of them. The new 8th Gen NVENC now accelerates AV1 encoding, besides HEVC. You also get an "optical flow accelerator" unit that is able to calculate intermediate frames for videos, to smooth playback. The same hardware unit is used for frame generation in DLSS 3.
All GeForce RTX 4070 Ti Super graphics cards use the 12+4 pin ATX 12VHPWR connector, an adapter cable is included in the box.