GeForce RTX 4080 SUPER graphics card evaluation drops 1400 yuan, the new flagship of the game

After many twists and turns, RTX The 4080 SUPER public graphics card is still available. As the last graphics card in the RTX 40 SUPER series up to now, RTX 4080 SUPER is also one of the best in terms of performance. Today, we will bring you the NVIDIA GeForce RTX 4080 SUPER FE video card evaluation.

As an upgrade product of the entire RTX 40 series graphics card, the three products released at present are better than the prototype card of this model in terms of performance. In terms of price, RTX 4070 SUPER Official recommended selling price comparison of RTX 4070 It is regarded as adding quantity without adding price ； RTX 4070 Ti SUPER contrast RTX 4070 Ti Flat ； and RTX 4080 SUPER contrast RTX 4080 what is more Low one thousand and four hundred element 。

Judging from the pricing of the three SUPER series graphics cards, it is not difficult to find that NVIDIA's purpose is to gradually balance the price gap between the middle and high-end RTX 40 series graphics cards, and try to make its performance match the price.

Without further ado, let's take a look at the appearance of NVIDIA GeForce RTX 4080 SUPER FE video card.

one Overview of NVIDIA GeForce RTX 4080 SUPER FE

Among the three video cards released this time, two of them have released FE products. The RTX 4070 SUPER is more inclined to the middle end, and the card body is still relatively small, while the RTX 4080 SUPER card body is thicker and more textured.

Surprisingly, the adapter cable provided in the package is 8pin * 2 to 16pin. However, the recommended power supply of RTX 4080 SUPER is still 750W. Old users should pay attention to upgrading their computers.

Different from the earliest RTX 40 series FE version, the metal frame and font of this NVIDIA GeForce RTX 4080 SUPER FE version are also black, which looks like a beast waiting to be launched.

The overall size of NVIDIA GeForce RTX 4080 SUPER FE graphics card is about 310 × 140 × 61mm (excluding the baffle), occupying 3 slots. As a sub flagship graphics card, it is equipped with a larger heat dissipation module, and its volume is comparable to that of Kahuang RTX 4090.

The size of the NVIDIA GeForce RTX 4080 SUPER FE fan is larger than that of the RTX 30 series, and has basically reached the diameter of the overall frame of the graphics card. On the basis of the increase of the cooling fan, the maximum airflow dynamic increases by 20%, and the airflow dynamic increases by 15% at the same noise level.

The FE version of the SUPER series graphics card still has the appearance of a handicraft, but all surfaces are easy to be stained with fingerprints. If you want to collect, you are recommended to wear gloves and "play".

On the video output interface, the four interface design of HDMI 2.1+DP 1.4a * 3 is still adopted. HDMI 2.1 can support 4K 120Hz HDR and 8K 60Hz HDR.

Due to the dual axial flow cooling system adopted by the public version, a large number of cooling fins can be seen at the video output interface, and hot air can also be felt to be discharged from here after you get on the computer.

The whole card power consumption of NVIDIA GeForce RTX 4080 SUPER FE this time is 320W, and a single 16pin auxiliary power supply is adopted. The recommended power supply is 750W and above. After you get on the computer, the "GEFORCE RTX" on the side of the video card will emit white light, which will complement this black based video card.

two Analysis of NVIDIA GeForce RTX 4080 SUPER Architecture

The GeForce RTX 40 series graphics card released this time is built by the new NVIDIA Ada Lovelace architecture, and adopts the TSMC 4N NVIDIA customized process. The flagship core AD102 has achieved 76 billion individual transistor And 28 billion RTX 30 series graphics cards.

Compared with the previous generation NVIDIA Ampere, NVIDIA Ada Lovelace has More than twice Performance improvement up to 90-TFLOPS The shader data throughput of.

The RTX 4080 SUPER released this time has 10240 CUDA cores, providing 52-TFLOPS Computing power; 80 third-generation Ada RT cores have 121 RT-TFLOPS ； 320 fourth generation Tensor Cores available 836 Tensor-TFLOPS（AI TOPS） 。

The L2 cache capacity of RTX 4080 SUPER is 64MB, and the bandwidth is 736 GB/s. NVIDIA officials also showed the importance of L2 Cache. We use two figures to briefly illustrate the role of L2 Cache.

In a real GPU, the kernel is where all computing takes place, and This is the role of L1 data cache. Each SM has an ultra-low latency L1 data cache, next to its processing kernel, making L1 the first choice for GPU to find information. However, since L1 cache needs to be very close to the kernel, it cannot be very large.

If the data required for kernel computing cannot be found in the L1 cache, the GPU will look in the L2 data cache. This video memory system is located on the GPU chip and connected to all GPCs (graphics processing clusters) through a very high-speed crossbeam system. Each GPC includes multiple SMs. If the information is found in the L2 cache, the GPU will pick up the data and put it into the kernel.

If no information is found in L2 cache (called cache missing), GPU will search VRAM through video memory interface. This creates a lot of extra work in the entire GPU storage subsystem, and reduces performance and power efficiency.

For more detailed parameters, we have summarized a table for you. It can be seen that the RTX 4080 SUPER is closer to the RTX 4080 from all aspects of the specifications, and there is still a big gap between the RTX 4080 SUPER and the Kahuang RTX 4090.

In addition, the main price is 1400 yuan cheaper than the recommended price of the RTX 4080. On the one hand, the price of the RTX 40 series is too high for the first launch, but this upgrade of the SUPER series also shows enough sincerity. Let's look directly at the test results.

three Introduction to test platform

First of all, let's introduce the test platform. In order to ensure the performance of NVIDIA GeForce RTX 4080 SUPER, our platform still uses the latest i9-14900K, equipped with MSI Z790 ACE Ares, and the Hangjia three piece kit used for electromechanical devices.

Hangjia MVP Apollo Pro (Apollo Master Edition) adopts a panoramic column free design, which can be called a real "seascape room". The interior space is spacious, and it supports top class graphics cards such as ATX, MATX, Mini ITX motherboards and RTX 4090. In terms of structure, the left and right layered cooling design is adopted, the chassis accessories and power supply are independently cooled, and the sliding tempered glass side plate and double top cover reinforced design are adopted. It also supports the latest back plug-in motherboard, which is convenient for players to walk out of the cool back line. In addition, this chassis also adds a type-c interface, has 10 fan bits, and is perfectly compatible with 360mm water cooling. With MVP 120 small universe mute fan, it can achieve the effect of both heat dissipation, mute and "light pollution".

Core i9+RTX 4080 Super is a "dream combination", but it needs strong "logistics support" while achieving high performance. In this test, we chose Hangjia MVP P1200 platinum full module power supply, which is built based on ATX3.0 specification. It has a rated power of 1200W and has passed the 80Plus white gold certification. It is a powerful "heart" of the whole machine. Two PCIE5.1 interfaces are reserved, and a 12VHPWR module cable that can support 600W is collocated. The flagship Kahuang 4090 can easily cope with it. In addition, the fan of this power supply also supports intelligent start and stop, realizing the balance between performance and silence. It will continue to run for 60 seconds after shutdown, delaying the aging loss caused by high-temperature waste heat. It can be said to be a flagship product that takes into account all aspects.

As the strongest CPU of the 14th generation, the Core i9-14900K is best matched with a water-cooled radiator. We choose Hangjia MVP Posen V360 integrated water radiator. The water-cooling head is equipped with a quiet water pump with a long-life ceramic bearing. The bottom is equipped with a high-density copper bottom with spade teeth, which increases the contact area and improves the heat transfer efficiency; The cold exhaust is designed with 12 water channels and S-shaped fins to provide more heat dissipation. It is equipped with PWM fans with three long-life hydraulic bearings to further improve the heat dissipation efficiency. It also supports ARGB light effect, which can create perfect light effect. In addition, the reverse side of the water-cooling head is also equipped with a 2.4 inch IPS LCD display, which can not only display the CPU temperature and power consumption in real time, but also display customized pictures and video content in a variety of formats, making it more pleasing to invite wives into the chassis.

Now let's take a look at the video card parameters of this evaluation GPU-Z It is version 2.57, and the parameter identification is more detailed.

NVIDIA GeForce RTX 4080 SUPER has 10240 CUDAs and the Boost frequency is 2550MHz. However, judging from the current OC version of AIC's graphics card, NVIDIA has reserved a lot of space for overclocking this time.

The video card uses 16GB GDDR6X video memory with a bit width of 256bit. It is worth noting that although the video memory bit width RTX 4080 SUPER is the same as the RTX 4080, the video memory frequency is higher than that of the SUPER video card just released, so the overall bandwidth is also higher than the 716 GB/s of the RTX 4080.

The raster unit and texture unit are 112 and 320. The raster unit RTX 4080 SUPER is the same as the RTX 4080, but there are more texture units.

four Theoretical performance test

In this test, NVIDIA GeForce RTX 4080 SUPER mainly compares its upper and lower models, RTX 4080 and RTX 4090.

The first step is to measure the graphics card DX11 The 3DMRKFS package with theoretical performance: FS, FSE and FSU correspond to the theoretical performance of the graphics card at 1080P, 2K and 4K respectively. The actual test results of the graphics card scores are as follows:

In traditional 3DMARK In the "three board axe" test, the gap between NVIDIA GeForce RTX 4080 SUPER and RTX 4080 is not big, about 2%, and there is still a big gap between NVIDIA GeForce RTX 4080 SUPER and Kahuang RTX 4090.

Now let's take a look at the tests of some new specific application scenarios in 3DMARK.

Speed Way test combines real-time ray tracing and traditional rendering technology to measure the performance of video card. The scene contains raytraced reflections, real-time global lighting, mesh shaders, volume illumination, particles, and post-processing effects. So SW testing can basically be regarded as the benchmark of next-generation 3A games.

NVIDIA GeForce RTX 4080 SUPER, compared with RTX 4080, increases from 1080p resolution to 8K resolution as follows: 4%/3%/4%/1% 。

In addition, we used the DLSS 3 just updated by 3DMARK for relevant performance tests.

This test is more biased towards the actual game frame score, so the overall base is small. The comprehensive improvement of NVIDIA GeForce RTX 4080 SUPER is about 2%, but the actual frame number is not obvious.

In terms of the overall theoretical test results, NVIDIA GeForce RTX 4080 SUPER FE has a comprehensive improvement of about 2% compared with RTX 4080 in the traditional three tests of FS/TS/PR, and can reach about 5% if it is an OC version video card; In addition, compared with RTX 4090, the comprehensive gap is 25%.

five General game performance test

Since the new DLSS 3 technology is added to the RTX 40 series this time, a separate test will be carried out later. Here we still select several mainstream 3A masterpieces for game performance comparison.

First of all, we tested the recently popular "Eudemon Paru". This game comes with DLSS, so the N card is easier. In addition, although the game is made with a fantasy engine, the overall content of the game at the EA stage is relatively rough, so the requirements for the graphics card are not very high.

We choose the highest image quality for frame number measurement. NVIDIA GeForce RTX 4080 SUPER can achieve a high frame rate of e-sports even at 4K resolution. However, this kind of simulated construction games will change gradually with the increase of world content, so the above test results are for reference only.

There are five picture quality levels in the game "Eudemon Paru", of which the difference between the highest and the lowest is large. The main difference lies in light rendering, anti aliasing and vegetation, and the difference in materials and maps is small.

Then there are some old friends. In Extreme Racing: Horizon 5, NVIDIA GeForce RTX 4080 SUPER has significantly improved compared with RTX 4080. However, due to the CPU bottleneck at 1080p resolution, the scores of the three video cards are almost the same. The RTX 4090 can still feel the CPU bottleneck at 2K resolution, while the 4K resolution can better reflect the true level of the three video cards.

On《 Assassin's Creed In Fantasy, NVIDIA GeForce RTX 4080 SUPER increases by 3% compared with RTX 4080 respectively: 1080p; 2K increased by 4%; 4K increase by 6%, comprehensive increase 4% 。

In Land Without a Master 3, NVIDIA GeForce RTX 4080 SUPER has a 9% increase in 1080p compared with RTX 4080; 2K increased by 8%; 4K resolution increased by 8%, comprehensive improvement 8% 。

Light pursuit test of bright memory: infinity Software It is a test tool independent of the game, which is more than the ray tracing technology used in the game. The test condition is "the highest RTX/DLSS quality".

In terms of performance, compared with RTX 4080, NVIDIA GeForce RTX 4080 SUPER increases by 8% for 1080p; 2K increased by 6%; 4K increase by 2%, comprehensive increase 5% 。

In the score running software of another domestic game Border, the situation is basically the same as that of Bright Memory: Unlimited, and the test conditions are all conducted under the "highest RTX/DLSS quality".

In Frontier, compared with RTX 4080, NVIDIA GeForce RTX 4080 SUPER increases by 11% at 1080p; 2K increased by 6%; 4K increased by 7%, comprehensive improvement 8% 。

In Cyberpunk 2077, a "game test benchmark", the latest light pursuit overspeed mode has been added, resulting in more achievements. We compare the frames in different modes.

NVIDIA GeForce RTX 4080 SUPER can achieve 98 frames of amazing results in the light chase overspeed mode at 1080p resolution. As the benchmark of the current light chase game, the overspeed mode in Cyberpunk 2077 is known as the ultimate form of ray tracing, adding a new path tracing, which also has a qualitative leap compared with the light chase super mode. Strictly speaking, it is not the "product" of this generation of games, so it is more for game developers as a technology foresight.

In addition, at 2K resolution, the super mode of light pursuit we often contact can also reach 100 frames, and the super mode of light pursuit can reach the smooth level of 69 frames.

In the final test, we will experience different light and shadow modes in Cyberpunk 2077.

From top to bottom, it is super image quality/ray tracing super/ray tracing: overspeed mode. You can see the ray tracing: the overspeed mode is closer to the real effect than the ray tracing super mode. It simulates the real ray path. In fact, compared with the previous ray tracing, it simulates the reflection of more rays on different surfaces, completely calculates the real lighting of the scene, and avoids the "dead black" situation in the previous generation of ray tracing.

In addition, Cyberpunk 2077 has updated DLSS 3.5 to support light reconstruction technology. In the above test diagram, it is not difficult to find that ray reconstruction can more accurately calculate the effect of the reflection part. In the reflection close to the bright metal surface, the obvious difference in image quality can be seen without turning on RTX, so it will not be repeated. The key point is the switching effect of DLSS 3.5. In addition to the clearer content displayed on the billboard, the detailed appearance of the distant wires and buildings in the industrial area can be seen after magnification.

In the conventional street water surface reflection, DLSS 3.5 not only correctly reflects the distant light, but also can more finely show the outline of the light tube. In addition, when RTX ON/DLSS is OFF, the shadow of the ashtray in the screenshot in contact with the ground is obviously true. After DLSS 3.5 is turned on, it also has a more correct object relationship.

six DLSS 3 performance test

Up to now, more than 500 games and applications have supported RTX technology.

The DLSS 3 technology will be supported by Dragon Creed 2, Grey Zone War, Half Life 2 RTX, Horizon: The West's Dead End, Layers of Fear, Dragon 7 in Man: The Unknown Dragon, Dragon 8 in Man, Nake Garden: The Last Paradise, Pax Dei, Star Miner and Kingship and Freedom, Some of these games will be released this year, while others will update their support for DLSS 3 this year, bringing unprecedented performance and higher image quality to gamers equipped with GeForce RTX 40 series graphics cards.

This DLSS 3 adds 1% Low FPS and delay tests, 1% Low FPS arranges the number of frames in a period of time from large to small, selects the smallest 1%, and then averages the 1%.

This time, we tested the frame number of DLSS 3 for Cyberpunk 2077 under three levels of image quality, and enabled DLSS quality record frame number for all levels.

It can be seen that at 2K resolution, even in the light pursuit overspeed mode, the performance of 100 frames can still be achieved after DLSS 3 is turned on, which is epic for the progress of the game screen.

DLSS 3 technology is mainly aimed at CPU bottleneck games, so it can also be seen that the lower the resolution, the greater the frame number increases, and 1080p can reach about 40%.

After the 1.8.86 version of Starry Sky was updated, DLSS 3 was added. The overall effect is very good. Even at 4K resolution, it can reach the smooth level of 111 frames.

Among them, DLSS 3 is 44% higher than DLSS 2 at 1080p resolution; 2K resolution increased by 56%; 4K resolution increased by 44%.

Although the frequent image reading of Star Sky, which has been criticized, has not been modified, at least for users who use the N card, the smoothness of the image can be greatly improved.

Horizon 5 is also an old friend of video card testing. Its excellent optimization enables many entry-level products to run at a higher frame rate. It is also evident in NVIDIA GeForce RTX 4080 SUPER. In the three resolutions, the improvement of DLSS 3 over DLSS 2 is 41%/29%/14% 。

Finally, we also tested Wizard 3: Hunting Madly. After ray tracing was added to this game, the requirements for configuration rose sharply.

Among them, NVIDIA GeForce RTX 4080 SUPER, under 4K resolution, turns on DLSS 3 instead of turning off DLSS, which is improved to 108% ； Compared with DLSS 2, the improvement has also reached 53% 。 In addition, Reflex Boost will be forced to be enabled after DLSS 3 is enabled, which can greatly reduce the picture delay.

seven Productivity tool testing

V-Ray

In terms of productivity tools, we tested the latest version of V-Ray renderer, and selected CUDA test and RTX test using GPU rendering. The results are shown in the figure below.

Blender

Blender is a professional 3D rendering software, which has launched a fixed benchmark Score running software, eliminating installation software download The trouble of material. The software will automatically render three scenes of the test monster/junkshop/classroom.

The above figure shows the score of NVIDIA GeForce RTX 4080 SUPER graphics card, 4475/2103/2192 points respectively, with an average of 2923 points.

D5 renderer

D5 is a domestic real-time ray tracing renderer, which supports direct reading of various modeling software, including SketchUp 、 3Ds MAX , Rhino, Revit, Archicad, Blender, C4D, etc. At present, DLSS 3 is also supported. Let's take a look at the frame number and power consumption respectively.

Select the default scenario of the software [Simple Living Room]

In terms of real-time frame number, as D5 uses real-time GPU rendering, the pressure is all on the graphics card. It can be seen that at 4K resolution, even NVIDIA GeForce RTX 4080 SUPER is in PPT status, with only 21 frames. After DLSS 3 is enabled, the frame number can be increased to 262% Around, very violent.

In terms of power consumption, the TDP of NVIDIA GeForce RTX 4080 SUPER is 320W. When DLSS is turned off, the actual average power consumption is 282W. After DLSS 3 is turned on, the power consumption is only 211W. Lower power consumption, higher It can be said that DLSS 3 is not only a great help for game players, but also a more necessary technical blessing for content creators.

eight ON1 Resize AI 2023 test

This test adds the test of ON1 Resize AI 2023, which is an AI image repair software, including image zooming, content filling and other functions. It can also be used as PS And other software in the form of plug-ins, which is very convenient and fast.

Five high-resolution images provided by NVIDIA were selected for the test. We will directly enlarge the size of the original image by 200%. It can be seen that the size of the enlarged image has reached 12000 × 8000.

After AI calculation with NVIDIA GeForce RTX 4080 SUPER FE, the final time of five pictures is 34641ms, or about 35 seconds.

Use NVIDIA ICAT for comparison after zooming in, and the left side uses ON1 Resize AI 2023 enlarges the image by 200%, and it can be seen that the coding in the tire part is clearly clearer than the original image.

In the other picture in contrast, the veins of leaves are clearer and the whole picture looks sharper after AI zooming in. It's really amazing for a picture with a magnification of 200%.

AI is indeed more convenient for the application of daily life. In our previous understanding, image size enlargement will inevitably lose quality. However, with the blessing of AI, it is clearer, which plays a more convenient role in repairing old photos.

nine AIGC test

I don't know when the AI era has become closer to people's lives, ranging from text rewriting to various generative AI. We have tested the AI drawing ability of Stable Diffusion before, but now NVIDIA has launched a new TensorRT plug-in, which can fully call Tensor computing power. Let's test NVIDIA GeForce RTX 4080 SUPER FE Performance in this regard.

[Note: xformers optimization scheme is enabled by default for all tests]

The first is the relatively basic SD1.5 model test. In SD1.5, the output resolution of the model is 512 × 512 and 768 × 768. We will export the [TRT] engine and record the default model rendering and the batch time of [TRT] model rendering.

Output according to the unified parameters provided by NVIDIA, so as to record the results. The sampling method is Euler a; Sampling steps: 50; Batch Count：10

[Default SD1.5 model] NVIDIA GeForce RTX 4080 SUPER operation time 22.2s, about 2.22 seconds

[TRT SD1.5 model] NVIDIA GeForce RTX 4080 SUPER operation time 14.7s, about 1.47 seconds

The second test is the SDXL model test of. The SDXL model will be trained at a resolution of 1024 × 1024. Compared with SD1.5, the image is twice larger. It can provide more accurate keyword matching, thus obtaining more realistic results. However, due to the higher original resolution and model complexity, the computational strength of the SDXL model is significantly higher.

We set according to the same parameters, but the size is specified as 1024 × 1024. Let's take a look at NVIDIA GeForce RTX 4080 SUPER FE How well they perform.

[Default SDXL model] NVIDIA GeForce RTX 4080 SUPER operation time 1m44.4s, about 10.44s

[TRT SDXL model] NVIDIA GeForce RTX 4080 SUPER operation time 1m11.4s, about 7.14 seconds

In more complex models, the advantages of TensorRT engine are increasingly obvious, and the output speed of a single image can be increased by about 3 seconds.

For ordinary users, generative AI can enable people without painting skills to independently create a work no less than that of an artist, so that everyone can become an artist in their own life.

At present, generative AI is only in the initial stage of development. Later, for personalized education, health care, language processing, even financial analysis and other scenarios, I believe that AI can be used.

ten RTX Video Super Resolution Test

At present, the RTX Video Super Resolution has been partially browser First, players need to update to the latest NVIDIA drive In the NVIDIA control panel, you can see the latest RTX video enhancement superresolution in [Adjust Video Image Settings].

RTX video super-resolution is a breakthrough in AI image processing. It goes beyond the traditional edge detection and feature sharpening technology and greatly improves the quality of live video content.

Enabling RTX video super-resolution requires not only the latest driver, but also the use of RTX 40 or 30 series GPU, and is almost suitable for Google Chrome And Microsoft Edge browser (the browser also needs to be updated to the latest version).

After opening, currently known users can enjoy the bonus of RTX VSR effect by opening YouTube or Station B.

If you are not sure, you can open the task manager when playing the video in full screen. When you see the GPU load increases, it means that the startup is successful.

We open YouTube to watch videos at will. After opening RTX VSR, we can clearly see that the quality of underwater coral has improved significantly, the edges are clearer, and the distortion is greatly reduced.

(Click to enlarge the original picture)

In the comparison of the following picture, it is obvious that after the RTX video super-resolution is turned on, the beard is obviously smoother, and the mosaic is no longer visible.

However, it should be noted that the effect of RTX video super-resolution is more obvious at low resolution. If the video you watch is 1080p or above 2K, it is difficult to see the difference.

This is very helpful for some users whose network speed is not fast enough, who can only watch low resolution videos, or the video source itself is not clear enough.

eleven Temperature and power consumption test

In the power consumption test, we selected FurMark software for copying test, and used GPU-Z to detect the temperature. The power consumption only calculated the graphics card itself.

It can be seen that NVIDIA GeForce RTX 4080 SUPER has passed the copying machine test for about one and a half hours, and the temperature is 65℃ About, the hot spot temperature is 74℃ about.

Game dynamic power consumption test

In this copy test, the maximum onboard power consumption is 300W The TDP is always around 95%. If the vehicle is fully loaded, it is around 320W. However, due to different game loads, the actual power consumption of GPUs is dynamic. Similar to the change of FPS over time, it is difficult for the RTX 40 series to reach the power consumption wall.

NVIDIA GeForce RTX 4080 SUPER 3A Average Game Power Consumption

In the actual game power consumption test, we chose Bright Memory: Unlimited, with its own benchmark, the highest light pursuit, DLSS quality, and 4K resolution, to reach the performance limit of the video card and test the power consumption of our actual application scenarios.

You can see that the average power consumption of NVIDIA GeForce RTX 4080 SUPER is 288W In the real machine test, the peak power consumption is basically less than 320W.

twelve Direct drop of 1400 yuan AI New choice Game new flagship

The upgrade of RTX 4080 SUPER is actually a "price cut" for players. The price difference of 1400 yuan is equivalent to the price of an entry-level video card. Although the official suggested price of 8099 yuan is still not cheap, it is a quasi flagship product with online performance.

Compared with the other two graphics cards in the SUPER series, the performance improvement of the RTX 4080 SUPER released this time is not so obvious, and there is still a big gap compared with the RTX 4090; In terms of parameters, it is also closer to the prototype card RTX 4080.

As an 80 level product, it locates the frame rate of traditional 3A games at 4K resolution. Even light chase games can reach a smooth level at 4K resolution.

Now, with the latest DLSS 3.5, even the distant light chase game in the past, players can have a smooth and unobstructed experience. Maybe when the next generation RTX 50 video card is released, the light tracking game of "path tracking" will become an effect that can be experienced by mainstream video cards.

In terms of AI, since the RTX 4080 SUPER was finally lifted, the results are quite obvious compared with the current SUPER series. SD is about 1 second faster than RTX 4070 Ti SUPER single picture; Compared with RTX 4070 SUPER, it is about 3-6 seconds faster. Although the gap is not big from a single perspective, SD mapping usually involves repeated debugging actions. Until the final mapping, it is still necessary to generate many batches and times before there can be satisfactory works.

In addition, in this new ON1 Resize AI 2023 test, the RTX 4080 SUPER also has a qualitative improvement over the two cards.

To sum up, if you are a heavy fan of AIGC, RTX 4080 SUPER is a useful productivity tool; If you only play occasionally, the SUPER series released this time is a good choice.

This article is an original article. If it is reproduced, please indicate the source: GeForce RTX 4080 SUPER graphics card evaluation drops 1400 yuan, the new flagship of the game https://diy.zol.com.cn/854/8546074.html