Shulou(Shulou.com)11/24 Report--

Last year's RTX 3060 Ti became a good choice for mainstream gamers because of its powerful performance. So the RTX 4060 Ti based on the new Ada architecture released this year is equally eye-catching. Everyone is concerned about whether the next generation of RTX 4060 Ti can continue the excellent performance of RTX 3060 Ti and the cost-effective performance of the 60 Ti series.

On the other hand, NVIDIA handed over two new cards, NVIDIA GeForce RTX 4060 Ti 8G and NVIDIA GeForce RTX 4060 Ti 16G. Their performance is almost the same, and they all have 32MB's L2 cache, resulting in a higher read hit ratio. The difference between the two is that the 16G large memory version is more suitable for accelerating AI content creation, while the 8G version is more cost-effective for 1080p high-frame games. Both of them have a performance improvement of 15%, 70% compared to RTX 3060Ti GDDR6, and a performance improvement of 60%, 160% compared to 2060 SUPER. It can bring high frame rate and low latency game experience at 1080p resolution.

CTOnews.com also received the public version of NVIDIA GeForce RTX 4060 Ti 8G in advance. In this test, we will use a set of high-configuration intel configuration to test, and the resolution will be adjusted to 1080p to avoid video card bottlenecks. The specific configuration is as follows:

The exterior design of the NVIDIA GeForce RTX 4060 Ti 8G is very similar to the NVIDIA GeForce RTX 4070 we tested before. The graphics card body is a standard 2-slot design with a length of only about 24cm, and the overall design is compact. Even the ITX chassis with A4 structure can be easily installed.

The only difference between the whole radiator and the NVIDIA GeForce RTX 4070 is that the metal edge next to it has changed from gun gray to silver gray, making it more flexible.

The front is a thick heat dissipation fin, the whole graphics card all-metal design is also conducive to heat dissipation.

The graphics card fan adopts a unique arrangement of one left, one right and one up and down, which can form a vertical air duct and better take away the heat on the fins.

The periphery of the graphics card is surrounded by a silver-gray all-metal edge with an eye-catching GeForce RTX logo printed on top.

The screw interface is designed on the right side, and the whole card has a strong sense of integration.

In terms of power supply, it uses the 16Pin power supply interface of the latest ATX3.0 specification, and the adapter from 1*8Pin to 16Pin is included in the package. this design is humorous, and we can see NVIDIA's determination to promote ATX3.0 standards.

In fact, its TGP power consumption is only about 160W, which can be driven by a single 8Pin power supply. Therefore, the vast majority of non-public version of RTX 4060 Ti choose a single 8Pin power supply design.

The I / O interface bezel uses the same dark gray color matching of RTX 4070, and the interface is equipped with 3*DP1.4a interface and 1*HDMI2.1 interface, supporting up to 8K60Hz output.

Core parsing RTX 4060 Ti is based on AD106 core. The overall architecture is similar to the RTX 4070 we tested before, but the GPC has changed from 4 groups to 3 groups, with a total of 4352 CUDA cores, 136 Tensor cores, 34 third-generation RT cores and 51 ROP units, which can basically be understood to retain the core size of RTX 4070. The signature NVENC video encoding unit and NVDNC video decoding unit still exist, which means that it is also very suitable for content creation.

The BOOST frequency for RTX 4060 Ti is 2535MHz, and the default frequency is 2250MHz. Video memory is 128-bit wide 8GB GDDR6 Hynix display memory, power consumption and heat are greatly reduced.

NVIDIA officials have also explained why they chose 128-bit 's flash memory, mainly because the storage subsystem of the new NVIDIA Ada Lovelace architecture has increased the size of the L2 cache by 16 times, greatly increasing the cache hit ratio. Nvidia said that historically, the display bit width has been used as an important indicator to determine the speed and performance level of the new GPU. However, the explicit memory bit width itself does not fully indicate the performance of the storage subsystem. On the contrary, it is helpful to have a more comprehensive understanding of the storage subsystem design and its overall impact on game performance.

As shown in the figure above, the L2 cache bandwidth in Ada GPU has increased significantly. This makes it possible to transfer more data between the processing core and the L2 cache. In various games and comprehensive benchmarks, 32 MB level 2 cache reduces video memory bus traffic by an average of more than 50% compared to the performance of 2 MB level 2 cache. This 50% reduction in traffic enables GPU to use its video memory bandwidth more efficiently, with a nearly two-fold increase in efficiency. Therefore, in this case, the performance of the isolated video memory performance of Ada GPU with 288 GB / s peak video memory bandwidth is similar to that of Ampere GPU with 554 GB / s peak video memory bandwidth. In a series of games and comprehensive tests, the greatly improved cache hit rate increased the game frame rate by up to 34%.

The above improvements in video memory utilization efficiency are all due to the latest NVIDIA Ada architecture, which is the latest architecture of NVIDIA, which is based on TSMC 4N NVIDIA customized process, thus achieving a leap of up to twice the performance and power consumption ratio. Its streaming multiprocessor throughput is more than twice that of the previous generation, and the ray-tracing computing power of the third-generation RT Cores is 2.8 times higher. In addition, the fourth generation of Tensor Cores added a FP8 engine with up to 1.32 petaflops of Tensor processing performance, more than five times that of the previous generation. SER technology brings up to three times the performance improvement for ray tracing, and up to 25% improvement for overall game performance.

The new Ada architecture provides amazing performance and energy efficiency for a variety of professional graphics, video, AI, and computing workloads, as well as many innovative features, such as:

1. A new optical flow accelerator is added, which can use AI to predict the motion changes in the scene, realize the frame generation technology of DLSS 3, and greatly improve the frame rate and image quality.

two。 Support AV1 encoder, can effectively compress the size of video files, while ensuring higher image quality. This is very useful for application scenarios such as video transcoding, streaming media, video conferencing, augmented reality and virtual reality.

3. The introduction of the RTX VSR function can achieve real-time video super-resolution, so that low-resolution video can also show clear details on the high-resolution screen.

It is worth mentioning that the interface adopted by RTX 4060 Ti 8G has also changed, from PCIe 4.0 to PCIe 4.0, which will not have any impact on players using the new motherboard. However, if your motherboard only supports PCIe3.0, then it runs in PCIe3.0*8 in practice, and the bandwidth will be affected to a certain extent. It is recommended to install the machine with a relatively new platform.

Theoretical performance We mentioned in the introduction that the power consumption of NVIDIA GeForce RTX 4060 Ti 8G is very low. How low can it be? We're going to test the grill. After 15 minutes, the core temperature was stable at 66.8 ℃, and the apparent storage temperature was about 78.2 ℃. The power consumption of the whole card is only 160W, which is not only much lower than RTX 3060 Ti, but even lower than RTX 3060. If the power supply is not false, CPU with i5, R5 and other 100-watt CPU, as long as 450W power can drive the whole machine, it has to be said that the energy efficiency ratio of Ada architecture and TSMC 4N custom technology is really very high, RTX 4060 series will also be good news for ITX players.

Next, there is a 3DMark pressure test, which can detect whether the performance of the graphics card has declined under continuous running minutes. Generally, more than 97% can be regarded as a qualified graphics card. The measured score of NVIDIA GeForce RTX 4060 Ti 8G is 99.5%, and the performance release is extremely stable.

In the 3DMark TimeSpy DX12 test, the video card score reached 13653. For comparison, RTX 3060Ti's score was 12277, an increase of about 10%, while the power consumption was much lower.

In the 3DMark FireStrike Extreme DX11 test, the score of the NVIDIAGeForce RTX 4060 Ti 8G graphics card reached 16194 points, compared with the RTX 3060 Ti score of 14553, an increase of about 10%.

In the 3DMark Portal Royal light pursuit test, NVIDIAGeForce RTX 4060 Ti 8G got a score of 8056. For comparison, the score of RTX 3060 Ti was 7158. It seems that the theoretical performance of RTX 4060 Ti 8G is about 10% compared with RTX 3060 Ti.

After the actual measurement of the game, we will carry out the actual measurement of the game. The resolution is adjusted to 1920 to 1080, and the image quality is adjusted to the highest. If you have light, you will open the most high-end light pursuit, and if you have DLSS, you will open it to the quality file. The first is the competitive game "CS:GO", which shows the performance of the RTX 4060 Ti 8G in high frames. After running the built-in BenchMark, the average frame reaches 537 frames, which can meet the needs of high-frame play, and can run all kinds of video games.

It is worth mentioning that 70 games have supported NVIDIA Reflex low-latency technology, of which eight major competitive shooting games support NVIDIA Reflex, including "Apex Hero", "call of Duty: theater 2", "Destiny 2", "Escape from Takov", "Fortnite", "Watchman Vanguard", "return", "Rainbow 6: siege" and "Dauntless contract". The author expects CS2 to add NVIDIA Reflex support after updating Origin 2, so that all popular FPS games can enjoy the advantage of low latency.

Next, the author also tested two classic 3A masterpieces. "Wild Dart 2: redemption" can reach an average of 115 frames with a quality of DLSS, which is already good for 100 frames of high definition. This 1080p experience is undoubtedly excellent.

We got a similar answer in another classic 3A masterpiece, Tomb Raider: shadow. Running the built-in BenchMark at the highest 1080p picture quality has reached an average of 212frame, which means conquering the 2K resolution is not a problem.

In the light chase masterpiece "Control", when the maximum light chase is turned on, it can even reach 144 frames, and it is no longer a dream to play the light chase 3A masterpiece with e-sports 's number of frames.

What really opens the gap between the RTX 4060 Ti and RTX 3060Ti is its DLSS 3 technology, which leverages the fourth-generation Tensor Core and optical flow accelerators on AI and GeForce RTX 40 series GPU to generate more high-quality frames, resulting in a significant increase in the number of frames. DLSS 3 is the latest version of NVIDIA deep learning oversampling technology and a revolutionary breakthrough in neural graphics technology, which can improve performance by up to 4x while maintaining picture quality and reaction speed.

To put it simply, the past DLSS 2 technology improved image quality and frame rate by rendering a low-resolution image and then zooming in to a high resolution through AI. On the basis of compatibility with DLSS 2, the new DLSS 3 technology adds a frame generation function, which can insert a new frame calculated by AI between two real frames, so as to double the frame rate. At the same time, combined with the super-resolution function of DLSS 2, AI can reconstruct up to 7/8 display pixels, and the game performance can be up to four times better than without DLSS!

So far, more than 300 DLSS games and apps have been released. There are more than 30 released DLSS 3 games. In terms of the progress of the release, DLSS 3 was adopted seven times faster than DLSS 2 in the first six months of the release of DLSS 2 and DLSS 3 respectively. It seems that the difficulty of adaptation is quite low. I believe that more and more games will adapt to DLSS technology in the future.

Let's first take a look at the frame number of the most stressful "cyber punk 2077" at + 1080p resolution. By default, RTX 4060 Ti 8G still has no way to play, with an average of about 45 frames. If DLSS 2 quality is turned on, the average number of frames can reach 79 frames. And if you open the exclusive cool techs DLSS 3 of the RTX 40 series, it will soar to an average of 119 frames in an instant.

Legendary 3A masterpiece "Wizard 3: hunting" has also recently updated the next generation version, the configuration requirements have been greatly improved, of course, the picture quality has also kept up with the trend, and it is not out of date today. At the same time, it also provides DLSS 3 technology support, which is undoubtedly good news for RTX 40 series graphics cards.

The next-generation version of "Wizard 3: hunter" has an average of only 43 frames in GeForce RTX 4060 Ti 8G with 1080p resolution without DLSS. If you turn on quality file DLSS 2, you can achieve an average of 65 frames of smooth play. If AI-enhanced DLSS 3 technology is enabled, the number of frames can soar to an average of 102frames, and most scenes can achieve the highest 1080p special effects of 100 frames.

In another next-generation 3A masterpiece, the Legend of the Plague: Requiem, the optimization is relatively much better. Even if you do not turn on any AI technology, you can play smoothly at 1080p 60 frames, and you can play with the number of e-sports frames after DLSS 3 is added.

The measured RTX 4060 Ti 8G can already satisfy 60 frames of free play without turning on the DLSS technology. If you turn on the DLSS 2 quality file, you can achieve an average of 84 frames, and if you turn on DLSS 3 inserting frames, the number of frames will soar to an average of 110frames, meeting the needs of high-brush displays.

So, how much will the GPU of the 60 Ti series improve from generation to generation? The author replaced this configuration with RTX 3060 Ti GDDR6 (OC) to test a set of data to see how much performance will improve between generations and how much will be improved with the blessing of DLSS 3 technology. When DLSS 3 is not enabled, RTX 4060 Ti 8G has an advantage of about 15% in frame number. If you turn on the DLSS 3 technology exclusive to the RTX 40 series, the number of frames will generally nearly double that of the previous generation, and the effect is really excellent.

As we mentioned earlier, the power consumption of the RTX 4060 Ti 8G is quite low, which can actually be driven by a single 8Pin power supply. So we also use Nvidia's official FrameView tool to count the average power consumption in each 3A masterpiece. The measured data surprised the author that the actual power consumption in most 3A masterpieces is about 130W-140W, which is even lower than the power consumption assigned to GPU by many notebooks. In this way, DIY players do not need to buy big power at all, and ITX players can look forward to the launch of a large number of single fan RTX 4060 Ti.

Creative production of the NVIDIA GeForce RTX 4060 Ti series has also been given a certain amount of creative production capacity, and the graphics card supports the installation of NVIDIA Studio drivers to accelerate more than 110 of the most popular creative applications. Proprietary SDK makes these applications run faster and provides exclusive features such as Optix, DLSS, and Maxine. NVIDIA Studio has a full range of creative applications, including NVIDIA Omniverse, Broadcast, Canvas and RTX Remix. If you choose to buy 16G large display memory version, it also has a certain generative artificial intelligence computing power, and there is no problem to use it for simple AI painting training. However, the 16G large memory version has not yet been released, so let's do a simple test with the 8G version.

The CUDA core of the NVIDIA GeForce RTX 4060 Ti 8G provides hardware acceleration for increased productivity. Almost all modeling software optimizes NVIDIA's GPU, so it can take into account efficiency, stability and compatibility. For example, in the commonly used rendering tool V-Ray, you can take advantage of the ray tracing feature of RTX acceleration to achieve high-performance final frame rendering. In addition, GPU with AI noise reduction can further accelerate interactive rendering and provide a smoother work experience.

We also measured the performance of V-Ray Benchmark, and GeForce RTX 4060 Ti 8G scored 1360 points, which can meet some medium-scale modeling and rendering requirements.

Thanks to the improvement in light pursuit performance, the score of GeForce RTX 4060 Ti 8G in V-Ray GPU RTX has also increased to 1919, which can also meet the needs of some medium load light pursuit modeling rendering.

We also test the performance of GeForce RTX 4060 Ti 8G in Blender. The measured results are as follows. We can see that GeForce RTX 4060 Ti 8G has a very good acceleration effect on this kind of modeling work.

In the later part of the video, the GeForce RTX 4060 Ti 8G is also equipped with an NVENC encoder. And RTX 4060 Ti 8G also supports the next generation video coding technology AV1,AV1, which can provide faster video coding and higher quality streaming media transmission performance while occupying the same space. As the major video platforms want to save the cost of server traffic, AV1 coding will become the mainstream coding method in the future.

We did a little experiment. In the professional version of clipping, a video with the same resolution and the same bit rate is derived, one coding protocol chooses the traditional H264, and the other chooses the next generation AV1 coding. As a result, the volume of H264 coding is 140m and the volume of AV1 coding is only 106m, which is much smaller on the premise of ensuring the image quality.

And the author also found that the video exported by GeForce RTX 4060 Ti 8G, which supports AV1 codec, can be accelerated by the video card and can be suppressed in only 8 seconds.

But GeForce RTX 3060 Ti does not support AV1 coding hard solution, can only use CPU soft solution, export time is as long as 1 minute 26 seconds, take dozens of times longer. It can be said that the RTX 40 series GPU is a sharp weapon for video workers to "fight for the future".

CTOnews.com also tested the PugetBench For Adobe family bucket to see if it could do the video editing job. Measured GeForce RTX 4060 Ti 8G in the Adobe Premiere commonly used by creative workers, we enable GPU Cuda acceleration, and then use PugetBenchmark to test. With a final score of 1188, there is no pressure to browse 4K videos on the timeline.

We also use PugetBenchmark for testing in Adobe Effects, another more stressful video special effects software. The final score is 1504, which can be used to produce some more complex visual effects.

In addition to video content production, RTX 4060 Ti 8G also provides RTX VSR technology in the field of video content consumption. The full name is RTX Video Super Resolution (RTX Video Super Resolution Technology). It can increase the resolution of online 1080p video to 4K at most through AI calculation of GPU. At present, this technology has adapted to Chrome browser and Edge browser, as well as local player VLC.

The use of RTX video super resolution is very simple, as long as the driver of the RTX 30 series / 40 series is updated to the latest version, and the Chrome / Edge browser is updated to the latest version. Enable the path as follows: NVIDIA Control Panel-Video-adjust video image settings. There are four gears available under this option box. The higher the gear, the more obvious the super-resolution effect, but it will also consume more GPU resources.

At present, it already supports domestic mainstream video platforms (bilibili, Douyu and Huya), as well as some foreign video platforms (Youtube, Twitch, Netflix, Hulu and Disney+). It also supports local video super resolution. In the following test, after the resolution of the leftmost native 480p is overscored, the following 1-4 gear can be seen more clearly, and the actual look and feel is comparable to that of 4K.

↑ is 480p, VSR1, VSR2, VSR3, VSR4 from left to right.

To sum up, in terms of pure theoretical performance, the NVIDIA GeForce RTX 4060 Ti 8G is about 10% higher than that of the previous generation. Of course, the AI era is coming, and with the help of DLSS 3 technology, the number of frames of 3A masterpieces can be easily doubled. Although there are only a few dozen games covered by DLSS 3, judging from the speed of DLSS 2 adaptation, we are not far from the popularity of DLSS 3. In our actual experience, RTX 4060 Ti 8G can meet the requirements of playing 3A masterpieces in 100 frames with the highest picture quality of 1080p, and e-sports games can run with extremely high picture quality and ultra-low latency, which is suitable for players with a budget of about 5000-7000, as well as for players who are still using RTX 20 series and previous veteran cards to upgrade.

In terms of price, the price of the NVIDIA GeForce RTX 4060 Ti 8G FE version is set at 3199 yuan, and it is expected that the price of the third party of the non-public version will come below 3000, which will be a good choice for newly installed players. If you want to use it for productivity, don't look forward to the subsequent release of the 16g large memory version of the NVIDIA GeForce RTX 4060 Ti.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.