Last week Nvidia lifted the curtain on the performance of their new flagship, the Blackwell-based RTX 5090 as well as giving people their first look at DLSS 4. Both Founders Edition and aftermarket versions of that card hit stores on Thursday, January 30^th. Also announced with the RTX 5090 was the RTX 5080, which will be hitting stores on the 30^th as well, and over the past week I have had the RTX 5080 Founders Edition in the office and have put it through our benchmark suite. Today we can take a closer look at the card design and then see how it performed in those tests. It has an MSRP that is half of the RTX 5090, will it still impress with its performance? Let’s find out!

Product Name: Nvidia RTX 5080 Founders Edition

Review Sample Provided by: Nvidia

Written by: Wes Compton

Amazon Affiliate Link: HERE

What is new?

Nvidia announced a lot with this one so let’s try to touch on as much as we can. They of course had a few hardware announcements for the 50-Series. They have announced four cards, the RTX 5090, the RTX 5080, the RTX 5070 Ti, and the RTX 5070. That is the new 50-series RTX family. The slides below include their focus on them. The 5090 for example is targeted at 4k 240 Hz and the other three are targeted at 2k or 1440p performance. They all have GDDR7 VRAM with the flagship RTX 5090 having 32 GB and a 512-bit interface. The RTX 5080 cuts that in half to 16 GB, the RTX 5070 Ti also has 16GB, and then the RTX 5070 has 12 GB.

The new GPUs are based on the Blackwell architecture and they do have new updated RT and Tensor cores with that being the 4^th gen for the RT Cores and 5^th gen for Tensor cores. The new tensor cores can now also handle floating point (FP) 4 along with FP8 and FP16. They also have introduced an AMP processer which is the AI Management Processor to help schedule AI tasks alongside of graphics rendering. They have increased the number of NV encoders and decoders, it now depends on the card model and isn’t a flat number of them across the entire generation of cards. They have also moved to PCIe Gen 5 and DisplayPort 2.1b including UHBR20. For pricing the RTX 5090 comes in at $1999, the RTX 5090 is half that (just like its memory) at $999. The RTX 5070 Ti is $749 and the RTX 5070 is $549.

Some of the main goals with Blackwell were to optimize the neural workloads and reduce the memory footprint. No big surprises there. Memory is one of the more expensive parts of the cards and anyone who has been paying attention knows that neural workloads and AI have been where Nvidia has been seeing the biggest improvements. Combining those things they have brought AI into shaders with neural shaders. The example of this they show is a hair being rendered with ray tracing and how using spheres rather than triangles helps use less data which means less VRAM and higher frame rates.

Nvidia announced Transformer which replaces CNN as the model they use with Super Resolution. They have improved the design significantly to get better detail when scaling this up. On top of that, they announced DLSS 4 which has improved on the frame generation that they introduced with DLSS 3. It is now Multi Frame Generation. Where before they were able to generate every other frame, they can now do x3 or x4. This gets interesting once they add in DLSS Super Resolution as well because that is already rendering ¾ of the image. With both, they are rendering 15 of 16 pixels using AI. Of course how well this works then depends a lot on how good the renders are. But it gives huge improvements in performance and with frame generation, we know that those improvements still happen even if you are PCU limited for example. The example they show has DLSS off at 27 FPS, turning on Super Resolution it goes to 71 FPS. DLSS 3.5 gets you to 140 FPS and DLSS 4 is 248 FPS. DLSS is already supported by a LOT of games and Nvidia is saying that DLSS 4 will have 75 games and apps supporting DLSS 4 at Day 0. Some of those will be by using the Nvidia App, which can override the DLSS settings on some games. It is also important to note that some of these features will go back and work with legacy cards as well. Specifically, DLAA is going to work back to the 20 series of cards, same with the improved DLSS Super Resolution. The new multi-frame generation however only works with 50 series cards.

They also introduced a new Nvidia Reflex. Reflex helps improve responsiveness to get lower latency through the entire pipeline. Were Reflex offered 50% faster responsiveness the new Reflex 2 gets you 75% by using frame warp. They say that is coming first to 50 series and will be available in games like Valorant soon.

Below I have the specifications for the RTX 5090 as well as the last two xx90 cards. We can see that the number of GPCs hasn’t changed from the 4090 to the 5090 but they did increase the SMs from 128 to 170. The CUDA core SM count is still the same but there are now 21760 CUDA cores to the previous 16384, a 32% increase. We still have 4 Tensor SMs but the new 5^th gen design has 680 cores now. For clock speed, the RTX 5090 is set lower than the RTX 4090 with a clock speed of 2407 MHz. There are 32%more RT cores which is a 32$ increase but the RT FLOPS has jumped up 66% with the new RT design. The memory has increased from 24 GB up to 32GB and it now uses GDDR7. They have also increased the memory interface up to 512-bit from 384-bit which the 3090 and 4090 both had. The memory data rate has gone from 21 Gbps up to 28 Gbps and the bandwidth increased with that and the larger pipeline from 1008 GB/sec up to 1792 GB/sec a 77% increase. The cache has increased in side with the L1 cache going from 16384 KB up to 21760 KB and the L2 increasing as well from 73728 KB up to 98304 KB. The TGP also had a big jump going from 450 watts on the RTX 4090 to 575 watts here on the RTX 5090. This is an even bigger gap when you include the RTX 3090 which was 350 watts. The manufacturing process is still the TSMC 4nm 4N process so no changes there I mentioned it earlier but all of the 50 series cards moved to PCIe gen 5 and the RTX 5090 is no different. For pricing, it has an MSRP of $1999 which is $400 more than the RTX 4090 but is similar to the RTX 3090 Ti which also launched at $1999 back in 2022.

Above I have a more in-depth specification listing for the RTX 5080 along with the RTX 5090 and the two previous generations of xx80 cards with the RTX 3080 and RTX 4080. The RTX 5080 is running on the GB203 GPU, not the same GPU as the 5090. It has 7 GPCs which matches the previous model (the 4080) but it does have mode TPCs with 42 over 38 and SMs with 84 over 76 but those are both significantly lower than on the RTX 5090 which had more than twice that. That can be seen as well with the CUDA cores which are at 10752 a 10.5% increase from the 4080. I was curious, the 4080 was 11.7% over the 3080 so it isn’t completely out of line from generation to generation but it is down slightly. The 5080 has the highest clock speed of the four cards at 2617 MHz. For memory, it has 16GB of GDDR7 with a clock speed of 30 Gbps, which is the same capacity as the 4080 which had 16GB as well but it did step up from GDDR6X to 7 and the clock speed was increased by 34%. It has the same 256-bit memory interface that the 4080 had but is a step down from the 320-bit on the 3080. Overall memory bandwidth has increased from 760 GB/s on the 3080 and 716 on the 4080 up to 960 GB/s. The pixel fill rate was just a small improvement from the 4080 at 4.4% but the texel fill rate is better at 15.4%. The 5080 has a little more L1 cache but is the same on the L2 cache which both look small when compared to the RTX 5090. They have also added more video engines. The RTX 5080 has 2 NVENC and 2 NVDEC engines which is one more NVDEC compared to the 4080 and one of each compared to the 3080. They are also newer versions with the NVENC being 9^th gen and NVDEC being 6^th gen, one step up on both compared to the 4080. For power the RTX 5080 does have a higher TGP, both the 3080 and 4080 were 320 Watts, and the 5080 is 40 watts higher at 360 watts. The 5080 and 4080 are extremely similar in both die size and transistor count with the 5080 being just slightly lower on both which is interesting. Especially given that it is made on the same manufacturing node. The RTX 5080 uses PCIe Gen 5 just like the RTX 5090. For launch pricing the MSRP has bounced around a few times here. The RTX 3080 launched at $699 and the RTX 4080 launched at $1199. The RTX 5080 is in the middle at $999 which like I said in the opening is half the price of the RT 5090.

Before getting into testing I did also run GPUz to double-check that our clock speeds matched up with the specifications. The RTX 5080 Founders Edition was running with a 2617 MHz boost clock speed and that lines up with the stock clock speed of the RTX 5080. Beyond that the driver and BIOS version are noted for future reference, I tested the 5080 Founders Editon using the Nvidia 572.02 driver. That is a beta driver that was provided to the press ahead of the launch for testing.

Packaging

If you saw the packaging for the RTX 5090 last week, there aren’t any surprises here and you can go ahead and skip ahead. This just repeats what I touched on then.  Nvidia has been experimenting with a few designs including the previous generation of Founders Edition cards which used a corrugated material but the overall design did take up a lot of space. For this generation, the RTX 5080 Founders Edition’s box has a lot going on. The most surprising is that the outer shipping box is officially part of the packaging now where before they did have a shipping box that perfectly fit each card but the box inside was still what you might expect to see on a store shelf. This time around I’m told this brown box is the outer packaging and what retailers who carry the Founders Edition will have. This came to me with the shipping labels on it and also on the outside it has a large white sticker, similar to a laptop box, with the part number, BIOS version, SKU, and everything else printed on it. Where the 5090 had a second information sticker, our 5080 box didn’t have that.  The box has a seal that you rip off which reveals the quote “Inspired by Gamers. Enhanced by AI. Built by Nvidia”

When you open the brown box up all of the Nvidia branding is hidden away on the inside, which makes sense. If this is the box it will ship out in, you don’t want it to screen I have an expensive video card in here steal me. The front edge has stripes and the RTX 5080 model name and the stripes and Nvidia branding are on the underside of the lid. The box then has two arrows on the sides, you can pull these out and the side open to make it easier to get to the second box inside. This second box isn’t black like Nvidia has always done. This is also plastic-free where the previous design used a lot of plastic in it. The inner box is inkless and has flaps on the top and bottom edges that once you pull out allow the two halves of the box to come apart. They have die-cut the corrugated cardboard to fit the RTX 5080 Founders Edition inside so that it can't move around. In the past, the documentation and accessories were hidden under the card and that is still partially true here. But now they are hidden under the cool box inside the brown box. There is a smaller box and inside you have the quick start guide and the new power adapter.

The 12VHPWR connection ended up being a point of contention with the last generation of Nvidia’s cards. There were issues with melted connections and a lot of misinformation and quick reactions when it started to happen. The main reason they found was that the connection was sometimes not plugged in tightly and was often in tight bends because of it being on top of the cards. Combine that with a lot of the cables being stiff and you have a recipe for problems. Along with other changes that I will touch on when I get to look at the card itself. Nvidia did change the power adapter cable that comes with the cards. This new adapter has the same three 8-pin PCIe plugs that the 4080 had (this is one less than the 5090 and 4090 have) but they have individually sleeved the cables and made the cable longer. Those two things mean that it is significantly more flexible and won't put as much stress on the connection. The 12VHPWR end is a lot more robust as well with a thick body once you get past the cable needed to terminate all of those sleeved cables.

Card Layout and Photos

The RTX 5080 Founders Editon looks almost exactly like the RTX 5090 Founders Editon that I took a look at last week with the only exception being the cast fan shroud has a dark grey finish not a black finish. The overall design manages to look like all of the other Founders Edition designs while also changing things up. It has the infinity loop shape that gives it that X shape in the middle of the card but this generation Nvidia has changed things up with both fans now being on one side of the card, not with one on each side like last generation. The RTX 5080 Founders Editon is 304 mm long and 137 mm tall, just like the 4080 and 4090 from last generation but the new design is thinner with it being a proper 2-slot card, not 3-slots like previously. It is still a large card with its length and height, but the thinner profile should help with some SFF cases and in server farms where they want to pack as many into a small space as they can. One of the main reasons they managed the thinner design is a very unique PCB design which has almost all of the PCB packed into the center section between fans. They then have two breakout boards, one for the display connections and the other for the PCI 5.0 connection at the bottom of the card. I am curious if that means the card will be more repairable, a damaged PCIe slot might be replaceable in the right hands.

The side view of the RTX 5080 Founders Editon gives us a better look at both of the fans and the double flow through thermal design as Nvidia calls it. They have heatpipes that run the length of the card that are built into the heatplate over the center PCB, five in total. They then run out across both fans helping pull the heat from the center of the card out to the two main heatsink halves. Both fans take advantage of the full height of the card to fit, they are 115mm edge to edge and sit in a 120 mm fan opening. They both have 7 blades and a ring that wraps around the entire fan to give it more strength. They are axial and blow down into the card and out the back with the blow-through design. It still looks like magic on the left fan side where you have all of the display connections but can see right through it all in that area.

Up on the top edge of the RTX 5080 Founders Editon, the thick cast shroud wraps around on the front and back of the card, then in the center, there is a black cap that wraps around to both sides and over the top. That cap has the power connection tucked away in it recessed down and sitting at an angle. This new configuration is a lot better at preventing any strain on the connection. On top of that, the power connection itself is now a 12V-2x6 connection. It uses the same 12VHPR cable that the RTX 4080 used, but on the card itself the connection now has .25mm longer pins for each of the power connections and the sense pins on the back are 1.5mm shorter. The idea is that you get a better connection easier, but the now shorter pins will pick up if you don’t have it plugged all the way in. Combined with the new adapter that was also included should help prevent melting issues. Also on the top edge, the card has the GeForce RTX branding which is backlit. I don’t mind the simple branding, but I still think it would be cooler to get the model name here backlit instead. Showing off you have an RTX 5080 is cooler than GeForce RTX.

With the two fans being on the front side of the RTX 5080 Founders Edition, it’s no surprise that on the back side of the card, we don’t have a fan like with past Founders Edition cards. This side has the same infinity loop shape with the metal shroud making an X in the center of the card. You can’t see it, but there is backlighting between the X and the heatsink fins. Both sides have horizontal heatsink fins that fill almost the entire card. It is hard to see it, but behind the fans, the fins do have a convex shape to them. Beyond that this side has the black center sections that wrap around from front to back, the top section has the RTX 5080 branding on it, flipped upside down so it will be readable in your case.

Looking around at the top, bottom, and the end of the card we can see that Nvidia’s blow-through design doesn’t cheat with venting anywhere else other than two small vents at the center on the top and bottom. The metal shroud wraps around the end without any vents but does have two removable screws that can be used for attaching a support to the card. With a minimal amount of vents at the bottom it does mean that you won’t have much hot if any being blown down onto your motherboard, a lot of boards have their M.2 drives hidden there and the extra heat can be an issue with the PCIe 4.0 and 5.0 drives.

For display connections, the RTX 5080 Founders Edition has four in total. There are three DisplayPort 2.1b connections with UHBR20 and then one HDMI 2.1b down at the bottom. What is interesting is with the full blow-through design this end of the card is completely sealed up as well. Like with the RTX 5090 Founders Edition, the 5080 has a fully blacked-out PCI bracket which looks great. I’ve been pushing for this for years, they always look great and when the card is installed it better blends in with the case.

Getting the RTX 5080 Founders Edition and the RTX 500 Founders Edition next to each other shows that they are both the same size. The only difference between the two cards is the different finish color. The 5080 has a lighter finish which is similar to what Nvidia used for the RTX 4090, the RTX 5090 on the other hand is darker, basically black.

Before getting into testing I also got a few pictures of the RTX 5080 Founders Edition with the lighting lit up. The V-shaped accent lights on both sides of the card are completely hidden away when you look at the card when it is turned off but lit up you can see them well. Then up on top, the GeForce RTX branding is backlit as well. All of the lighting is white which looks great with the card and is neutral for just about any build, that said I do wish that RGB was an option, this could look cool lit up with the Nvidia green or in a color that matches your PC.

Test Rig and Procedures

 Test System

CPU: AMD Ryzen 7 9800X3D – Live Pricing

Motherboard: ASUS ROG Crosshair X870E Hero – Live Pricing

Cooling: Enermax LIQMAXFLO 360mm Liquid CPU Cooler - Live Pricing

Noctua NT-H2 Thermal Paste - Live Pricing

  Memory:   G.SKILL Trident Z5 Neo RGB Series (2x16GB) 6000MT/s CL28-36-36-96 – Live Pricing

Storage:   Viper VP4300 Lite 4TB – Live Pricing

Power Supply: be quiet! Dark Power Pro 13 1600W- Live Pricing

Case: Primochill Wetbench - Live Pricing

OS: Windows 11 Pro 64-bit - Live Pricing

Synthetic Benchmarks

As always I like to start my testing with a few synthetic benchmarks. 3DMark especially is one of my favorites because it is very optimized in both Nvidia and AMD drivers. It's nice to not have to worry about it being favored too much either way and the repeatability of the results makes it a nice chance to compare from card to card, especially when comparing with the same GPU. In this case, I am curious to see how the RTX 5080 Founders Edition compares with the RTX 5090 FE, but the better comparisons will be against the previous xx80 cards and from AMD the 7900 XTX.

The first round of tests were done in the older Fire Strike benchmark which is a DX11 test. There are three detail levels, performance, extreme, and ultra. The RTX 5080 Founders Edition scored a 79045 in the base Fire Strike test sitting above the RX 7900 XTX but below the RTX 4090. It was an improvement over the RTX 4080 by 20%. In Fire Strike Extreme it scored a 39871, putting it over the 7900 XTX again and behind the 4090 by a good margin. That is a 20% over the RTX 4080 once again. Then for the last Fire Strike test, Fire Strike Ultra the RTX 5080 Founders Edition is once again sitting above the 7900 XTX and below the 4090 but the gap between it and the 4090 is larger here. Its 21262 score put it as a 24% improvement over the RTX 4080.

The next two were both based on the Time Spy benchmark. One is the standard test and then there is the extreme detail level. For the standard Time Spy, the RTX 5080 Founders Edition scored a 32642, once again sitting between the RTX 4090 and the RX 7900 XTX. Compared to the RTX 4080 it was a 16.8% improvement, a little lower than what we saw in the DX11-based Fire Strike tests. For Fire Strike Extreme it scored a 16244, a 17.9% improvement over the RTX 4080 and it sits way out in front of the RX 7900 with its 14786. The RTX 4090 however is still significantly higher with a score of 19009.

I did also test using the new 3DMark Speed Way which is one of their latest benchmarks and Port Royal as well. Speed Way is DX12 as well but combines more future-focused tech like Ray Tracing which up until its release where only used in feature tests, not full benchmarks. The RTX 5080 Founders Edition isn’t sitting ahead of the 7900 XTX for this test, the 7900 XTX was down lower in the chart and the RTX 5080 Founders Edition is way out in front of the 4080 SUPER here with its 9039 score putting it 23.4% ahead of the RTX 4080 and 41% over the RTX 4080 SUPER. For Port Royal the result is similar, 24.8% ahead of the RTX 4080 and 21.9% ahead of the RTX 4080 SUPER.

The last test is the newer 3Dmark Steel Nomad benchmark. Officially this is the replacement for the Time Spy benchmark. It is a DX12 benchmark and doesn’t include ray tracing but is updated to better take advantage of modern cards. The RTX 5080 Founders Edition has a larger lead over the two RTX 4080s and the RX 7900 XTX here with its 8198 score putting it 25.8% ahead of the 4080, 24.6% ahead of the 7900 XTX, and 22.6% ahead of the 4080 SUPER. It is still behind the RTX 4090 here but the gap is a little smaller than in the other tests.

In-Game Benchmarks

Now we finally get into the in game performance and that is the main reason people pick up a new video card. To test things out I ran through our new benchmark suite that tests 8 games at three different resolutions (1080p, 1440p, and 4k). Most of the games tested have been run at the highest detail setting and a mid-range detail setting to get a look at how turning things up hurts performance and to give an idea of whether turning detail down from max will be beneficial for frame rates. Cyberpunk 2077 is also tested with Super Sampling (DLSS/FSR/XeSS). In total, each video card is tested 60 times and that makes for a huge mess of results when you put them all together. To help with that I like to start with these overall playability graphs that take all of the results and give an easier-to-read result. I have one for each of the three resolutions and each is broken up into four FPS ranges. Under 30 FPS is considered unplayable, over 30 is playable but not ideal, over 60 is the sweet spot, over 120 FPS is for high refresh rate monitors, and 240 helps show the performance ideal for the latest higher refresh displays.

So how did the RTX 5080 Founders Edition do? Like with the RTX 5090, at 1080p it just rolled through everything. Every result was above 120 FPS and 12 of the 18 results were over 240 FPS. Nvidia officially has the RTX 5080 Founders Edition targeted at 2k or 1440p performance which is why it has significantly less VRAM compared to the RTX 5090. That said it went through all of our 1440p tests without issues but this time there were more results in the 120-239 FPS range than those that were above 240 with 10 and then 8. At 4k we see the first results end up in the 60-119 FPS range which is still smooth and playable but a majority were still in the 120-239 FPS range with 2 over 240, 12 in the 120 range, and 4 in the 60 FPS category. Overall this shows that 4K is still capable here but a high refresh 1440p display would pair with it well. 

To get a better look at some of the cards that are the closest competition to the RTX 5080 Founders Edition I have all of the results averaged out and listed by the resolution. This does a great job of showing how the RTX 5080 compares to the RTX 4090. In our synthetic tests the RTX 4090 was consistently out in front but in our game tests, you see that is only the case at 4k. The 4090 has more VRAM and a 384-bit memory interface to the 256-bit on the RTX 5080 and it shows. At 1440p and 1080p however the 5080 moves out in front. Compared to the RTX 4080 the 5080 is 25% faster at 4k, 20% at 1440p, and 16% at 1080p.

Of course, I have all of the actual in game results as well for anyone who wants to sort through the wall of graphs below. All of the graphs are sorted by their 4k results so across the board the RTX 5080 comes in third on all of the results but when looking at the 1440p results you see it jumping ahead of the RTX 4090 in about half of the results.

Another new addition to my testing was a few additional tests using Cyberpunk 2077. This is one of only a few games that support most of the tech from all three of the GPU companies. So I did tests at medium and ultra detail while having Super Sampling on for all of the cards. Using whatever the latest and greatest is supported. In this case, I tested with DLSS  with frame generation on (DLSS 3) and also again with Frame Generation turned up to x4. Just a note here, the AMD cards only allowed FSR when running windowed mode whereas Nvidia only performed well in fullscreen mode. In the base tests and with DLSS 3 on the RX 7900 XTX comes in ahead of the 5080 but the 5080 does outperform the 4090 in the DLSS 3 results. In the results with frame generation x4 turned on however performance is significantly better. The RTX 5080 FE goes from 94 FPS at 4k ultra detail to 209 FPS with DLSS 3 and then up to 332 with frame generation x4 on. If you are gaming at 1440p with it on you will see 490 FPS with ultra detail and 600 FPS with medium detail.

Compute and AI Benchmarks

Now some people don’t need a video card for gaming, they need the processing power for rendering or 2D/3D production, or in some cases, people who game also do work on the side. AI performance importance has increased quickly recently as well. So it is also important to check out the compute and AI performance on all of the video cards that come in. That includes doing a few different tests. To start off our AI tests I ran Geekbench AI, a cross platform AI benchmark that uses real world machine learning tasks giving three results, a full precision score, half precision score, and quantized score. The RTX 5080 Founders Edition is sitting just below the RX 7900 XTX on this chart because it is sorted by the quanitized score, but with the half-precision score that story changes significantly.

Blender is always my favorite compute benchmark because the open-source 3D rendering software is very popular and it isn’t a synthetic benchmark. With the latest version of Blender, they redid the benchmark so we now have a new test that runs three different renderings and gives each a score. I have all three stacked together so we can see the overall performance. The RTX 5080 Founders Edition comes in ahead of the RTX 4080 SUPER and behind the RTX 4090 here with it sitting much closer to the 4080 SUPER than the 4090.

For CUDA-based cards, I also check out V-Ray Benchmark 5 to check out CUDA and RTX performance in the 3D rendering and simulation software. The RTX 5080 Founders Edition is sitting between the RTX 4080 SUPER and the RTX 4090 here once again and like with Blender it is closer to the 4080 SUPER than the RTX 4090 which is way out in front here with its additional VRAM and larger memory interface.

RTX and DLSS

Alongside the introduction of the new Blackwell-based  GPUs, Nvidia had multiple new announcements on the tech side of things with their newest version of DLSS 4 with its addition of Multi Frame Generation. They also have Deep Learning Anti-Aliasing (DLAA) and Transformer-based models to continue to improve the detail and accuracy of the AI-generated frames. So I am excited to see how it all performed. First up though I do have our standard 3Dmark DLSS comparison which I ran on every Nvidia card from the last two generations. For this test, I tested them all at 4k using the performance setting. I ran the same test with DLSS off, and then with DLSS 1, 2, 3, and 4 to compare the performance between them. Adding in the DLSS 4 results from the RTX 5090 and RTX 5080 broke the scaling of our graph and that puts some perspective on the performance difference that you can see when frame generation gets switched up to x4. For the RTX 5080 Founders Edition, it is interesting to see how the base frame rate was 49.11 and with DLSS 1 it jumps up to 88.48 and then up to 121.9 with DLSS 2. DLSS 3 with frame generation was another big jump, up to 169.01 but it is small compared to the 295.06 with DLSS 4. That is a 500% increase. This is a synthetic test that doesn’t change paths at all, so DLSS is going to handle it better than in a standard game but it is a look at the possibilities.

I also wanted to take a look at DLSS 4 performance as well a little more than my initial look at it with 3DMark’s benchmark. For this, I put Nvidias Frameview to the test to run a few benchmarks using the games that currently support DLSS 4. For games with a built-in benchmark, I ran the benchmark but used frameview so we could get the FPS and 1% lows. All of the tests were done at 1080p, 1440p, and 4k with the highest detail settings including the highest RTX settings. A few of these games had to be run on beta copies, namely Cyberpunk 2077, Hogwarts Legacy, Alan Wake 2, and Star Wars Outlaws. Marvel Rivals and Dragon Age both were on the public version but just used NV App’s override.

The first game tested was Dragon Age: The Veilguard and for this one, I did a test with DLSS 3 and 4 as well as with it off on all three resolutions. Like in our 3Dmark tests, this does a great job showing the performance improvements you can see with DLSS 3 or 4. The RTX 5080 FE went from 63 FPS at 4k and up to 145 with DLSS 3, a 130% increase, and then up to 261 FPS with DLSS 4 for a 314% increase. That takes the playable 63 up into nice smooth ultra-high refresh rate smoothness.

For Hogwarts Legacy, I kept things simple with DLSS 4 on or off. At 4k it jumps from 54 FPS up to 286 and even at 1440p it was worth the improvement going from 95 FPS up to 354. The 1% lows aren’t as tight to the average FPS as they were with DLSS off, but they do improve as well.

I tested the RTX 5080 Founders Edition out in Star Wars Outlaws. This was a comparison between the game with DLSS off and with DLSS 4. I saw significant improvements at all three resolutions and with the settings fully cranked (ultra detail, RTX direct lighting on and on ultra, cinematic lens turned on and on ultra) the game struggled at all three resolutions. Even at 1080p, we averaged 55 FPS and at 1440p and 4k it was barely playable. Turning DLSS 4 on however fixed that with 4k going from 18 to 68 FPS (277% increase), 1440p going from 36 to 131(263% increase), and 1080p going from 55 to 200 FPS(263% increase).

Next up was Cyberpunk 2077 and I changed things up here. This game had the option to switch between the Transformer and CNN models so I wanted to see what the performance difference between them was. The new Transformer model makes a significant improvement in the visual quality but as you can see here it does tradeoff performance slightly at all three resolutions. That improvement is worth it even if the tradeoff was a lot bigger than this, but it is important to note. That said, just using DLSS 4 in general turns unplayable performance when running Cyberpunk with every detail and ray tracing setting cranked up into smooth playable performance At 4k you go from 19 FPS up to 149 and that is the worst case situation. At 1440p it goes from 38 to 298 and at 1080p you go from 63 up to 481.

For Marvel Rivals I put the RTX 5080 to the test and compared the results between DLSS off and DLSS 4 on at all three resolutions. Titles like this typically don’t struggle even at the highest resolutions. In this case at 4k its DLSS off result was 79 FPS which is more than playable, but turning DLSS 4 on you see a 267% increase in performance with DLSS 4 going up to 290 FPS. At 1440p you go from 139 to 409 for a 194% increase. But at 1080p the improvement is even better going from 151 up to 545 for a 260% increase. You might not think this is important because you are starting with playable or even smooth performance, but it takes you up into the 290/409/545 range making ultra-high refresh displays possible.

For the last test, I took a look at Alan Wake 2 with DLSS 4 or with frame generation turned off. The game doesn’t give the option to turn off the other DLSS features but frame generation itself offers a huge performance difference and you can see that here. At 4k you go from 28 up to 99 FPS for a 253% increase. At 1440p you go from 58 up to 119 which doubles the performance but we can see we still have the same frame cap issue that is exclusive to the 1440p results, I saw the same with the RTX 5090 testing previously. Then at 1080p, we go from 89 up to 297 a 233 improvement.

Cooling Noise and Power

For my last few tests, rather than focusing on in game performance, I like to check out other aspects of video card performance. These are also the most important ways to differentiate the performance between cards that have the same GPU. To start things off I took a look at power usage.

For this, our test setup utilizes the Nvidia-designed PCat v2 along with cables to handle both traditional 6 or 8-pin connections as well as 12VHPWR. The PCat also utilizes a PCIe adapter to measure any power going to the card through the PCIe slot so we can measure the video card wattage exclusively, not the entire system as we have done in the past. I test with a mix of applications to get both in game, synthetic benchmarks, and other workloads like GeekbenchAI and AIDA64. Then everything is averaged together for our result. I also have the individual results for this specific card and I document the peak wattage result. I do have to note that during my testing of the RTX 5090 and not the RTX 5080, I ran into issues with a few tests, especially with OpenCL which is what AIDA64 uses to do their stress tests. I ended up having to replicate our test results using OCCT. To get as close as possible I used the 3D Adaptive stress test in OCCT and using the 4090 I stress tested it and played around with settings to get to a setting where OCCT replicated the same power usage and card temperatures. In the future, once that issue is fixed I will be redoing our 5090 and 5080 tests with AIDA64, but this issue was confirmed to be reproducible by Nvidia the day before launch and I didn’t have time to retest the whole list of cards tested. That said the OCCT result wasn’t the peak power usage here, so any difference between the tests will only change the average result slightly (but that same testing affects our temperature tests and power efficiency graphs. The RTX 5080 FE averaged 389 watts across our tests and peaked at 422 watts when running Time Spy Extreme. This put it above the RTX 3080 but below the RX 7900 XT. The RX 7900 XTX that ran behind it in our testing averaged 41 more watts and last generations RTX 4080 was farther down in the chart with an average of 339 watts.

With having exact peak wattage numbers when running Time Spy Extreme I was also able to put together a graph showing the total score for each watt that a card draws which gives us an interesting look at overall power efficiency in the popular and demanding benchmark. The higher power draw of the RTX 5080 Founders Edition compared to the RTX 4080 and RTX 3080 was offset by its increased performance. In fact, it is sitting up near the top of the chart behind the new RTX 5090 and ahead of the RTX 4090. AMD’s 7900 XTX is down further with a 31.5 Score per Watt to the 5080s 38.4 and everything in between those two are Nvidia’s 4000 series cards from last generation.

My next round of tests were looking at noise levels. These are especially important to me because I can’t stand to listen to my PC whirling. Especially when I’m not in game and other applications are using the GPU. For my testing, though I first tested with the fan cranked up to 100% to get an idea of how loud it can get, then again at 50% to get an idea of its range. The RTX 5080 Founders Edition was running at 41.4 decibels in our 50% fan speed test, this was better than the RTX 5080 and is an improvement over the 4080 FE and 4090 FE. With the fans turned all the way up it drops down in the bottom ¼ of the chart at 57 decibels. If you compare that with the RPM chart that does line up meaning the card isn’t noticeably louder or quieter than it should be for the RPM.

I also take a look at noise performance while under load. For that when running AIDA64’s stress test I wait until the temperature of the card has leveled off and then measure how loud things are when the card is at its worst-case scenario with the stock fan profile. Here the RTX 5080 Founders Edition was at 39.7 decibels and right in the middle of the pack compared to the other cards. When under load the fans were running at 42% fan speed which explains it being even quieter than in the 50% fan speed test.

To finish up my testing I of course had to check out the cooling performance. To do this I ran two different tests. I used AIDA64’s Stress Test run for a half-hour each to warm things up (on everything except the 5090 which was tested on a similarly matched OCCT workload). Then I documented what temperature the GPU leveled out at with the stock fan profile and then again with the fans cranked up to 100%. With the stock profile, the RTX 5080 Founders Edition leveled off at 66c, right in the middle of our chart. This was two degrees lower than the reference RX 7900 XTX and 6 less than the RTX 5090. It was 11 lower than the RTX 4090 which it runs the closest with. The memory was running at 66c as well. Then with the fans cranked up, the RTX 5080 Founders Edition dropped down to 55c which again was right in the middle of the pack and right with the RTX 4080 and a few other Founders Edition cards. That was 3c less than the RTX 5090 FE which has a similar cooler. The memory temps ran a little cooler at 54c. All said that was a delta of 11c between the stock and 100% fan speeds (again middle of the pack) which shows there is still some headroom left if you want to play with the fan profile and don’t mind a little more noise.

While running the stock fan profile testing I also took the time to get a few thermal images so we could see what is going on. For the fan side, the RTX 5080 Founders Edition is noticeably cooler than all of the motherboard below it and is cooler inside behind the fans. The top edge is running nice and cool on both ends of the cards and is warmer at the center where the PCB with the hottest spot being right at the power connection, but at 41c there isn’t anything to be concerned with. The hottest temps are on the back side where you have the “backplate” in the center where the PCB is the hottest at 48c. On the left heatsink, you can see the heatpipes running through as well.

Overall and Final Verdict

Tomorrow both the RTX 5090 and the RTX 5080 hit stores and if you have been reading up until now you may already have an idea of what you are planning on doing. If not I’m going to recap some of our coverage and then dive into where the RTX 5080 fits in the market. Nvidia’s new dual slot design changed the entire card up while surprisingly still giving the card that same signature Founders Edition look that all of the cards have. Part of that Founders Edition styling is the infinity loop shape that outlines the entire card with its cast aluminum shroud. The thick aluminum shroud design sets the Founders Edition cards ahead of a lot of the aftermarket cards on build construction. You never have to worry about a Founders Edition sagging or having those types of issues. They are heavy, but the construction is solid. With the RTX 5080 Founders Edition (and with the 5090 I previously took a look at) the PCB is mounted in the center of the card with the PCIe slot and display connections on breakout boards. This allows for a complete blow-through design with both of the cards fans. Another aspect that I didn’t consider before is that it might also make card repairs easier in the future in cases where the PCIe slot is broken or the display connections are broken which could be interesting. The unique card design allowed them to keep the card thinner which should help in some SFF cases and for servers that are packing as many cards as they can into a server. The card design is still tall and long, just like with previous xx80 and xx90 cards so there will still be some compatibility issues with some older cases. I know I’m going to have to upgrade from my Case Labs case to upgrade my GPU for example.

The new design now has a blacked-out rear PCI bracket, something I have been pushing for years to see cards move too. Not only does it match the card better, but it will also blend in better when installed in most cases as well. Its details like that put the Founders Edition up at or near the top for styling. Nvidia also made improvements to the power connection. It is now recessed and angled to reduce the possibility of strain on the connection. They have also improved the included power adapter and the connection itself on the card is now a 12V-2x6 plug which has longer pins to be less likely to get a bad connection and shorter sense pins to detect if it isn’t plugged in all the way. Hopefully, this addresses the issues that some users had with the previous design. Small details that I would love to see changed in the design style-wise. I would like to see the model name itself be the backlit branding up on top. I would much rather show off my RTX 5080 than the generic RTX GeForce branding. With that and with the accent lights on the front and back of the card, the white lighting that they went with looks great but I wouldn’t mind having the option to also change it to match a build if needed. BTW the new packaging is once again nothing I have ever seen before and also an improvement in sustainability as well, always cool to see that improve.

For performance, it will depend a lot on what your goal is for the card on whether you would say it did well in testing or not. Nvidia markets the card as a 2k or 1440p card and at that resolution and at 1080p it did extremely well, outperforming last generation's flagship RTX 4090. At 4k I would still say it did very well, but on average the RTX 4090 does edge back in ahead of it in our tests. The RTX 5080 has 16GB of memory and a smaller memory interface than the RTX 4090. It does have faster memory which makes up the difference a lot, but that does make a difference at 4k in some tests. That said, if you haven’t experienced DLSS 4 with the improved transformer models making significant improvements in the visual quality and frame generation x4 giving mind blowing performance, I would take that over the 8 extra FPS at 4k. Not only do you see a lot of those improvements even in CPU-limited situations, but you can see 300-500% performance improvements over not using DLSS at all. I didn’t run into as many of the bugs as I saw when testing the RTX 5090, but OpenCL-based workloads were still a problem but Nvidia is aware and working on it.

At the end of the day though, it always comes down to pricing. The RTX 5080 Founders Edition has an MSRP of $999. That is $200 less than the RTX 4080 launched at but is $300 more than what the RTX 3080 launched at. It’s also half of the price of the new RTX 5090. More importantly, how does it compare to other cards with current pricing? For that, I put the graph above together that takes every card I’ve tested’s Time Spy Extreme GPU Score and divides it by its current price as well as its launch MSRP. For current pricing, it is the lowest available price on PCPartPicker and it is interesting to see how much pricing and card availability has changed from last week when the performance of the RTX 5090 was shown. The RTX 5080 Founders Edition is sitting in the middle of the pack for value right now but there aren’t any cards faster or even near it in performance on the chart. With all of the talk on how it compares with the RTX 4090 for example, the only 4090’s you can currently get are $2598 or more. I wouldn’t call it a value, but if you are looking for high-end 1400p or 4k performance and the RTX 5090 isn’t in your budget this is the clear choice, that is assuming you can find these anywhere near the launch price once they hit stores.

Live Pricing: HERE

Author Bio

Author: garfi3ldWebsite: http://lanoc.org

Editor-in-chief

You might call him obsessed or just a hardcore geek. Wes's obsession with gaming hardware and gadgets isn't anything new, he could be found taking things apart even as a child. When not poking around in PC's he can be found playing League of Legends, Awesomenauts, or Civilization 5 or watching a wide variety of TV shows and Movies. A car guy at heart, the same things that draw him into tweaking cars apply when building good looking fast computers. If you are interested in writing for Wes here at LanOC you can reach out to him directly using our contact form.