Introduction

MSI GeForce RTX 4070 Ti Suprim X is the company's top-tier custom-design graphics card based on NVIDIA's latest salvo at the sub-$1000 performance graphics segment, with the new RTX 4070 Ti "Ada" that we're reviewing today. The Suprim X brand of graphics cards from MSI arose from a need within the company to match NVIDIA Founders Edition in aesthetics, while offering the best factory-overclock and OC headroom available in the market; while also differentiating itself from the company's Gaming X brand (something Gaming Z probably had less success doing). The GeForce RTX 4070 Ti is an interesting proposition, letting you play maxed out gaming at 1440p, or 4K Ultra HD gaming with reasonably good details, where you can take advantage of new features introduced with the RTX 40-series, such as DLSS 3 frame-generation, to dial up eye-candy even further.



The new GeForce RTX 4070 Ti "Ada" is a rebranding of what would have been the GeForce RTX 4080 12 GB, which NVIDIA cancelled in the face of criticism from the press and gamers on social media, over how vastly different the SKU is to the the RTX 4080 16 GB. Not only is the memory different, but the RTX 4080 12 GB is supposed to be based on a smaller silicon, with 21% fewer CUDA cores and RT cores; and a 25% narrower memory interface. NVIDIA originally intended to sell this at $900, but a "x80" card with a 192-bit memory bus would've crossed the line for some. The new RTX 4070 Ti launches at a trimmed down price of $800 (starting price), and a model number more appropriate for a product of this class.

The GeForce RTX 4070 Ti debuts the new 5 nm "AD104" silicon, which it maxes out, by enabling all 60 streaming multiprocessors (SM) physically present. This works out to 7,680 CUDA cores, 60 RT cores, 240 Tensor cores, 240 TMUs, and 80 ROPs. The card gets 12 GB of GDDR6X memory across a 192-bit wide memory interface, running at 21 Gbps. This yields 504 GB/s of memory bandwidth, which is much lower than the 608 GB/s of the RTX 3070 Ti, and the 760 GB/s of the RTX 3080 (comparable launch MSRP); but NVIDIA claims that it has generationally improved the memory sub-system at an architecture-level, with much larger on-die caches.

The MSI GeForce RTX 4070 Ti Suprim X is an attempt by the company to match the NVIDIA Founders Edition card in aesthetics, while also being the best-performing card you can buy, with one of the largest cooling solutions we've seen today, and possibly the best product design. Rich two-tone aluminium makes up the cooler shroud, with neatly executed RGB lighting. NVIDIA has standardized the 16-pin 12VHPWR power connector, and the card features it, along with an adapter that converts two 8-pin PCIe power connectors (2x 150 W) to one of these. This is just a means to tell the graphics card that the connector can supply no more than 300 W continuous, there's no physical difference with a standard 12VHPWR. MSI has also given the card its best factory-overclock, with the GPU Boost set at 2670 MHz, higher than the 2610 MHz NVIDIA-reference speed. MSI is pricing the card at $880, a steep premium over the $800 baseline price.

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.

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 leverages the TSMC 5 nm EUV foundry process to increase transistor counts. At the heart of this GPU is the new AD104 silicon, which has a fairly high transistor count of 35.8 billion, which is more than double that of the previous-generation GA104. The GPU features a PCI-Express 4.0 x16 host interface, and a 192-bit wide GDDR6X memory bus, which on the RTX 4070 Ti wires out to 12 GB of memory. The Optical Flow Accelerator (OFA) is an independent top-level component. The chip features two NVENC and one NVDEC units in the GeForce RTX 40-series, letting you run two independent video encoding streams (useful for game-streamers).

The essential component hierarchy is similar to past generations of NVIDIA GPUs. The AD104 silicon features 5 Graphics Processing Clusters (GPCs), each of these has all the SIMD and graphics rendering machinery, and is a small GPU in its own right. Each GPC shares a raster engine (geometry processing components) and two ROP partitions (each with eight ROP units). The GPC of the AD104 contains six Texture Processing Clusters (TPCs), the main number-crunching machinery. 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. There are 12 SM per GPC, so 1,536 CUDA cores, 48 Tensor cores, and 12 RT cores; per GPC. There are five such GPCs, which add up to 7,680 CUDA cores, 240 TMUs, 240 Tensor Cores, and 60 RT cores. Each GPC contributes 16 ROPs, so there are 80 ROPs on the silicon. The RTX 4070 Ti maxes out the AD104 silicon.


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 (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 introduces a revolutionary new feature that promises a doubling in frame-rate at comparable quality, it's called AI frame-generation. While it has all the features of 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. 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 frame-times with DLSS 3 are at an acceptable level, and a render-queue doesn't confuse the upscaler. 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

With the Suprim X, MSI has created a stylish elegant design that uses shiny metal surfaces of various textures, polish and color to create a unique product look. On the other side you'll find a high-quality metal backplate.


MSI has integrated three RGB illuminated elements in the front fans, one lighting element near the top, and one illuminated zone for the Suprim logo on the back.


Dimensions of the card are 34.0 x 14.0 cm, and it weighs 2030 g.


Installation requires four slots in your system.


Display connectivity includes three standard DisplayPort 1.4a ports and one HDMI 2.1a (same as Ampere).

NVIDIA introduces the concept of dual NVDEC and NVENC Codecs with the Ada architecture. This means there are now 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. 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.


The card uses the new 12+4 pin ATX 12VHPWR connector, which is rated for up to 600 W of power draw. An adapter cable from 2x PCIe 8-pin is included. Of course the 4x 8-pin to 16-pin adapter cables from RTX 4090 will also work with the RTX 4070 Ti.


This BIOS switch lets you toggle from the default quiet BIOS to the gaming BIOS, which runs a more aggressive fan curve.

Teardown

The main heatsink provides cooling for the GPU chip, memory chips and VRM circuitry. MSI has installed seven heatpipes.


Under the main cooling assembly, we find a secondary cooling plate that provides cooling for some more VRMs and improves the card's stiffness to protect against sagging.


The backplate is made from metal, it protects the card against damage during installation and handling.

High-resolution PCB Pictures

These pictures are for the convenience of volt modders and people who would like to see all the finer details on the PCB. Feel free to link back to us and use these in your articles, videos or forum posts.


High-resolution versions are also available (front, back).