Epilogue
The RTX 5090 is a powerful graphics card, the strongest available today. Still, I would be lying if I didn’t mention that I was expecting way more, after two years of the 4090’s release, especially in performance per watt. The 5090 pushes the 12V-2×6 connector to its maximum power delivery, 600W, so we already see problems with melted connectors and/or headers, even though very few RTX 5090 became available and sold so far. If the operating conditions are not close to the optimal ones, meaning high ambient temperatures, and if the 12V-2×6 cable is not of high quality or it is aged and extensively used (pulled in/out of the header many times), then you have the perfect recipe for disaster.
Unfortunately, NVIDIA’s engineers didn’t consider implementing per-pin OCP and OTP to protect the 5090 from overheating its header. This is why we are now developing a cable that will include these protection features. The cable will cut power to the graphics card and save the day if something goes wrong. But this is not our job; it should be NVIDIA’s in the first place.
While performance is high enough, I cannot say the same for performance per watt. The RTX 5080 and 5070 Ti are way more efficient, even the aged 4090 offers higher performance per watt in most scenarios I tested. Remember that all have to do with the games you use for benchmarking, and I used many popular game titles, and with numerous settings. I cannot cover all cases, but I try to provide the most complete picture of the RTX 5090’s performance.
In general I cannot recommend the RTX 5090 not only because it is an energy hog and it can be dangerous in the long (even the short) run because of its extremely high power consumption under stress, but it is also super rare to find (at the time of the review at least) and super expensive. I wonder why someone would pay so much money to get a graphics card like this one and always feel scared that its connector may melt. Usually I am not afraid while benchmarking and don’t have a problem leaving the test system unattended. Still, during some of the 5090 benchmarks, I caught myself worrying and checking the connector. I even installed thermal probes on it, to monitor it, noticing up to 65C operating temperatures on the 12V-2×6 connector on the GPU’s end, with a relatively low ambient, 22C, after ten minutes of 3D Mark Speed Way running at 4K (600W GPU power consumption).
You should also keep in mind that the PCIe 5.0 bus interface of most RTX 50 graphics cards, especially the FE ones, has compatibility issues with the PCIe expansion card that I use for Powenetics, with only the Galax RTX 5080 Ti working fine so far. This means that most PCIe extension cables will probably have issues and the only way to cope with this is to set the GPU’s PCIe bus to 4.0 through your mainboard’s BIOS. You won’t lose anything notable in performance, and you can use your PCIe extension cable(s) without issues.
ASUS TUF RTX 5090 vs. Asus ROG Strix RTX 4090 OC Edition (FHD, QHD, UHD Combined) | |||
Metric | FPS Improvement | FPS per Watt Improvement | |
Raster | +10.98% | -8.68% | |
+DLSS | -3.69% | -26.57% | |
+RT | +13.40% | -3.95% | |
+RT + DLSS | +8.98% | -9.24% | |
+RT + DLSS + FG (2x) | +15.23% | -2.31% | |
AVG: | +8.98% | -10.15% |
Without the option “+DLSS” where the 5090 is hammered by Warhammer and “The Last Of Us” the overall performance improvement on all three resolutions I tested (FHD, QHD, and UHD) is +12.15% from the RTX 4090, while the FPS per Watt loss is restricted to 6.05%. So choose what makes you feel better!
The graph below shows the significant differences between NVIDIA’s RTX generations. As you can see, MFG is only available for the RTX 50 line at the moment.
The other big news is the DLSS 4 Transformer model, which is not exclusive to the RTX 50 series but refers to all RTX lines. DLSS transformer models improve image quality with improved temporal stability, less ghosting, and greater detail in motion. There is a relatively small performance penalty, but as GPUs become more potent, we should focus more on quality than performance.
The following table reminds you of the differences between the RTX 50 series members.
RTX 5090 | RTX 5080 | RTX 5070 Ti | RTX 5070 | |
Architecture | GB202 | GB203 | GB203 | GB205 |
Process Technology | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N |
Base Clock (MHz) | 2010 | 2300 | 2300 | 2160 |
Boost Clock (MHz) | 2410 | 2620 | 2450 | 2510 |
VRAM Size (GB) | 32 | 16 | 16 | 12 |
VRAM Type | GDDR7 | GDDR7 | GDDR7 | GDDR7 |
VRAM Speed (Gbps) | 28 | 30 | 28 | 28 |
VRAM Bus Width (bit) | 512 | 256 | 256 | 192 |
Transistors (Billions) | 92.2 | 45.6 | 45.6 | 31.0 |
Shading Units | 21760 | 10752 | 8960 | 6144 |
TMUs/Tensor Cores | 680 | 336 | 280 | 192 |
ROPs | 192 | 128 | 96 | 64 |
SM/RT Cores | 170 | 84 | 40 | 48 |
TDP (W) | 575 | 360 | 300 | 250 |
Launch Month/Year | 1/2025 | 1/2025 | 1/2025 | 1/2025 |
MSRP ($) | 2000 | 1000 | 750 | 550 |
The Asus TUF RTX 5090 is a high power consumption and super expensive graphics card, offering a notable improvement over the previous flagship, the RTX 4090, mostly at 4K resolutions. The problem is that you won’t be able to find it at a price close to its MSRP, if you find it at all (at the time of the review). If you buy an RTX 5090, match it with an ATX v3.1 PSU with the proper, quality, high-power cable, and avoid using adapters. You will find the best ATX v3.x PSUs in this article.
- The faster GPU available today
- DLSS4 Frame Generation and Transformers Upscaling
- 32GB VRAM
- Fan stop feature for lower noise output
- HDMI 2.1 and DP 2.1 support
- PCIe 5.0 support
- High-end hardware encoding acceleration
- Quiet Operation
- Beefy cooling system
- Low operating temperatures
- Super expensive and rare to find
- Maxes out the 12V-2×6 connector/cable power delivery capacity
- Less power efficient than the RTX 4090 in most scenarios I tried
- Memory overclocking limited by the driver
- Large dimensions & heavy
- Prologue & Technical specifications
- NVIDIA’s Key Technologies
- Box & Contents
- Part Analysis
- Specifications Comparison
- Test System
- Game Benchmark Details
- Raster Performance
- RT Performance
- RT Performance + DLSS/FSR Balanced
- Raytracing Performance + DLSS/FSR Balanced + FG
- DLSS/FSR Balanced (No RT)
- DLSS/FSR Balanced + FG (No RT)
- Relative Perf & Perf Per Watt (Raster)
- Relative Perf & Perf Per Watt (Raster + DLSS/FSR)
- Relative Perf & Perf Per Watt (RT)
- Relative Perf & Perf Per Watt (RT + DLSS/FSR)
- Relative Perf & Perf Per Watt (RT + DLSS/FSR + FG)
- Rendering Performance
- Operating Temperatures
- Operating Noise & Frequency Analysis
- Power Consumption
- Clock Speeds & Overclocking
- Cooling Performance
- Epilogue
Can you do coil whine analysis? I’ve bought and returned so many cards because coil whine is unbearable with a silent pc.
In game menus, if there is no FPS limiter, most have coil whine, at desktop this is not the case.
Thank you for the review. Very good stuff.
When can we expect a review and the cybernetics report for the new FSP Mega TI 1350W PSU ? Looking forward to it i think it could be a very good performer at least i hope so.
Will ask from FSP review samples. Unfortunately lately I am over my head with work, and trying to find a solution on the 12V-2×6 thing, so limited time for PSU reviews.
Aris did Gamemax brings you some NDA for their new LION CORE PSU, i’ve seen that they just claimed tested & certified by Cybenetics ?
We did test a Gamemax PSU, but it is already on Cybenetics and it isn’t this model. I will look into this now that you mentioned it.
https://www.youtube.com/watch?v=D-7TbwosSC0 After watching this video, I want to ensure their brand never overclaims Cybenetics certifications. If they overclaim, it could be a fatal flaw. Alternatively, you can advise their brand to never overclaim that a product wasn’t tested by Yours.
I paired one with the FSP Hydro Ti PRO 1000W as you recommend in your tier lists, I was really looking forward to reviews of it!
Just received it 2 days ago and first impressions are great, I have it running at 45% constant fan speed and it’s increadibly silent, only when it gets closer to 65ºC or so I ramp up to 55% and there in really high loads it increases until 60% or so, keeping it under 70ºC without problems, while still being very quiet.
I tried a bit of undervolting and can do 0.93V with +412 MHz keeping pretty much 98% of the performance in 3DMark tests, and passing the Steel Nomad stress test.
I have measured the connector temperature with a FLIR E4 both at the PSU (~35ºC) and at the GPU (~55 to 65ºC as you say) while the stress test was running, I don’t see a problem at all. It’s clear that it gets hotter on the GPU as it is very close to the heatsink and very hot parts on the PCB.
I would be curious to see if you could do some undervolt analyses 🙂 I think there’s a lot of potential to reduce the crazy power it is uses. I agree that using it at maximum power for long times is bonkers, my entire computer enclosure was really hot after the stress test.
Cheers!
I also noticed in this graphics card, and not only, that the 12+4 header is so close to the GPU’s heatsink. It might not affect as much as I initially thought, but probably isn’t the best spot.
This period I am over my head with various projects and reviews, but I will do more work on the 5090 and examine more usage scenarios. This card required strong airflow for sure!
Yes, I have it in a good old Phanteks Enthoo Evolv (front modded) and it becomes a sauna in there…. But my 13700KF with a LF III modded to P12 MAX fans does a pretty good job to keep it cool in real usage scenarios, while the GPU also remains at decent temperatures.
I’m a big fan of silent PCs and I know that temperatures are not that big of a deal for electronics components (electronic engineer myself working in automotive industry) so I’m fine with that.
But of course, power is power and it has to go somewhere, so the environment around gets pretty warm.
Looking forward to seeing more tests when you have the time 🙂