Tuesday, February 25th 2025

NVIDIA GeForce RTX 50 Cards Spotted with Missing ROPs, NVIDIA Confirms the Issue, Multiple Vendors Affected

TechPowerUp has discovered that there are NVIDIA GeForce RTX 5090 graphics cards in retail circulation that come with too few render units, which lowers performance. Zotac's GeForce RTX 5090 Solid comes with fewer ROPs than it should—168 are enabled, instead of the 176 that are part of the RTX 5090 specifications. This loss of 8 ROPs has a small, but noticeable impact on performance. During recent testing, we noticed our Zotac RTX 5090 Solid sample underperformed slightly, falling behind even the NVIDIA RTX 5090 Founders Edition card. At the time we didn't pay attention to the ROP count that TechPowerUp GPU-Z was reporting, and instead spent time looking for other reasons, like clocks, power, cooling, etc.

Two days ago, one of our readers who goes by "Wuxi Gamer," posted this thread on the TechPowerUp Forums, reporting that his retail Zotac RTX 5090 Solid was showing fewer ROPs in GPU-Z than the RTX 5090 should have. The user tried everything from driver to software re-installs, to switching between the two video BIOSes the card comes with, all to no avail. What a coincidence that we had this card in our labs already, so we then dug out our sample. Lo and behold—our sample is missing ROPs, too! GPU-Z is able to read and report these units counts, in this case through NVIDIA's NVAPI driver interface. The 8 missing ROPs constitute a 4.54% loss in the GPU's raster hardware capability, and to illustrate what this means for performance, we've run a couple of tests.

In the first test, "Elden Ring" at 4K UHD with maxed out settings and native resolution (no DLSS), you can see how the Zotac RTX 5090 Solid falls behind every other RTX 5090 we tested, including the NVIDIA Founders Edition, a de facto reference-design that establishes a performance baseline for the RTX 5090. The Zotac card is 5.6% slower than the FE, and 8.4% slower than the ASUS ROG Astral RTX 5090 OC, the fastest custom design card for this test. Officially, the Solid is clocked at 2407 MHz rated boost frequency, which matches the Founders Edition clocks—it shouldn't be significantly slower in real-life. The interesting thing is that the loss of performance is not visible when monitoring the clock frequencies, because they are as high as expected—there's just fewer units available to take care of the rendering workload.

A ROP (Raster Operations Pipeline) unit in the GPU processes pixel data, handling tasks like blending, antialiasing, render-to-texture, and writing final pixel values to the frame buffer. In contrast, a shading unit, aka "GPU core" is responsible for computing the color, lighting, and material properties of pixels or vertices during the rendering process, without directly interacting with the frame buffer, so the performance hit of the eight missing ROPs depends on how ROP-intensive a game is.
For example, in Starfield, the performance loss is much smaller, and in DOOM Eternal with ray tracing, the card actually ends up close to its expected performance levels.

We've also put the card through a quick 3DMark Time Spy Extreme graphics score run.
  • NVIDIA Founders Edition: 25439
  • Zotac Solid: 22621
  • Gigabyte Gaming OC: 26220
This should be a number that you can test easily for yourself, if you're one of the lucky RTX 5090 owners. The quickest way is definitely to just fire up GPU-Z and look at the ROP count number, it should be "176."

So far, we know only of Zotac 5090 Solid cards that are affected, none of our review samples from ASUS, Gigabyte, MSI, Palit, and NVIDIA exhibit this issue, all 5090 owners should definitely check their cards and report back.

This is an issue with quality assurance at both NVIDIA and Zotac. NVIDIA's add-in card partners (AICs) do not have the ability to configure ROP counts, either physically on the silicon, or in the video BIOS, and yet the GPU, its video BIOS, and the final product, cleared QA testing at both NVIDIA and Zotac.

We are working with Zotac to return the affected card, so they can forward it to NVIDIA for investigation. At this time Zotac was unable to provide a statement, citing the fluidity of the situation. As for possible fixes. We hope the issue is localized to a bug with the driver or the video BIOS, so NVIDIA could release a user-friendly BIOS update tool that can run from within Windows and update the BIOS of the affected cards. If, however, the ROPs were disabled at the hardware-level, then there's little that end-users or even AIC partners can do, except initiating a limited product recall for replacements or refunds. If the ROPs really are disabled through fuses, it seems unlikely that NVIDIA has a way to re-enable those units in the field, because that would potentially provide details to how such units can be reactivated on other cards and SKUs from the company.

Update 14:22 UTC:
Apparently the issue isn't specific to Zotac, HXL posted a screenshot of an MSI RTX 5090D, the China-specific variant of the RTX 5090 with nerfed compute performance, but which is supposed to have 176 ROPs. Much like the Zotac RTX 5090 Solid, it has 8 missing ROPs.

Update 16:38 UTC:
Another card has been found, this time from Manli.

Update 17:30 UTC:
ComputerBase reports that their Zotac RTX 5090 Solid sample is not affected and shows the correct ROP count of 176. This confirms that the issue isn't affecting all cards of this SKU and probably not even all cards in a batch/production run.

Update 17:36 UTC:
Just to clarify, because it has been asked a couple of times. When no driver is installed, GPU-Z will use an internal database as fallback, to show a hardcoded ROP count of 176, instead of "Unknown." This is a reasonable approximation, because all previous cards had a fixed, immutable ROP count. As soon as the driver is installed, GPU-Z will report the "live" ROP counts active on the GPU—this data is read via the NVIDIA drivers.

Update 19:18 UTC:
A card from Gigabyte is affected, too.

Update Feb 22nd, 6:00 UTC:
Palit, Inno3D and MSI found to be affected as well

Update Feb 22nd, 6:30 UTC:
NVIDIA's global PR director Ben Berraondo confirmed this issue. He told The Verge:
NVIDIAWe have identified a rare issue affecting less than 0.5% (half a percent) of GeForce RTX 5090 / 5090D and 5070 Ti GPUs which have one fewer ROP than specified. The average graphical performance impact is 4%, with no impact on AI and Compute workloads. Affected consumers can contact the board manufacturer for a replacement. The production anomaly has been corrected.
Very interesting—NVIDIA confirms that RTX 5070 Ti is affected, too.

While NVIDIA talks about "one ROP unit," this really means "8 ROPs" in our context. Many years ago, marketing decided that higher numbers = better, so they started to report the number of pixels that can be processed per unit, instead of the actual unit counts. So in this case, one hardware unit is disabled, which mean eight pixels per clock less can be processed, resulting in a loss of "8 ROPs".

Update Feb 25th:
In the meantime, some RTX 5080 GPUs with missing ROPs were found, too, NVIDIA provided the following statement to TechPowerUp:
NVIDIAUpon further investigation, we've identified that an early production build of GeForce RTX 5080 GPUs were also affected by the same issue. Affected consumers can contact the board manufacturer for a replacement.
Add your own comment

491 Comments on NVIDIA GeForce RTX 50 Cards Spotted with Missing ROPs, NVIDIA Confirms the Issue, Multiple Vendors Affected

#376
brianinengland
soulphieYes, it seems like Nvidia fucked this up and mixed up 5090 and 5090D dies
Both models have the same number of ROPS, apparently
Posted on Reply
#377
Tropick
MacZI'm saying that you should be grateful to buy a $1,000 car when this company can sell $25,000 cars all day.

If you are not happy with the quality you get, you should stop buying the $1,000 car.
Okay I think I'm starting to understand what you mean. Nvidia could easily just leave the consumer space and we wouldn't have any of their GPUs at all and they'd still be able to make a killing. I guess my point is just that until they've actually left the consumer space they are still obliged to honor their advertising even if it's a product that only makes a fraction of the margin the more expensive product does. And we do have a right to be upset, in the same way that "if we're not happy with the quality we get, we should stop buying the cards." my counterargument would be that "If Nvidia isn't happy with having to spend full QA money to ensure their lower margin products meet advertised spec, they ought to not even sell them." But I see your point, consumers voting with their wallets is the only way to stop this sort of thing. It's just dissapointing to see an industry juggernaut like Nvidia choosing to rest on their laurels and cash in on their goodwill knowing their fans will likely blindly buy crummy quality dies they cordon off for us "non AI hyperscaler peasants". Guess I'm just missing the days when they had to keep us happy because the gaming crowd was their cash cow lol. Times have changed... Hey AMD where's that Navi 4C MCM anyways? :laugh:
Posted on Reply
#378
MacZ
Tropickmy counterargument would be that "If Nvidia isn't happy with having to spend full QA money to ensure their lower margin products meet advertised spec, they ought to not even sell them." But I see your point, consumers voting with their wallets is the only way to stop this sort of thing. It's just dissapointing to see an industry juggernaut like Nvidia choosing to rest on their laurels and cash in on their goodwill knowing their fans will likely blindly buy crummy quality dies they cordon off for us "non AI hyperscaler peasants".
First, companies don't care about 'fans'. Nobody should be a 'fan' of any company, whose sole aim is making money.

Second, To maximize AI GPUs production, they need to lessen gaming GPUs production. It means that the price of these gaming GPUs will go up, and having lower quality GPUs is a way to have a larger production than an otherwise stricter quality control would allow. Stricter quality control means even lower production (GPUs being discarded/repurposed) which means higher prices.

I think the quality issue is quite deliberate.

And it would be the same for AMD if they hadn't exited the high end GPU market or Intel if they were able.
Posted on Reply
#379
_roman_
W1zzardAbsolutely, the delta between the FE and the fastest factory OC'd card, the ASUS Astral is 4-5% only, so yes, this will definitely raise eyebrows, especially when a card drops to below FE levels
This is the reason some people overclock their cards for some percentage gain. A difference between a playable game and a slideshow.
Posted on Reply
#380
Hecate91
MacZSelling $2,000 GPUs when you could make and easily sell $25,000 GPUs instead is charity at this point. And not insulting the future.

You should be grateful that you are offered any GPU for gaming at all is what I'm saying.

AMD exiting the high end GPU market is just another fact that further validates my hypothesis.

And Intel is nowhere near able to compete there for now. But if they where, it would be the same thing.
Selling GPU's for $2000 is not a charity, not even close.
And you're saying we should all get on our knees thanking Jensen for selling defective GPUs?
No that isn't how it works, when you pay for something, you should expect it to work as it was advertised.
AMD and Intel has nothing to do with these issues, your argument is so far removed from reality it makes no sense.
Posted on Reply
#381
MacZ
Hecate91Selling GPU's for $2000 is not a charity, not even close.
And you're saying we should all get on our knees thanking Jensen for selling defective GPUs?
No that isn't how it works, when you pay $2000 for something, you should expect it to work as it was advertised.
AMD and Intel has nothing to do with these issues, your argument is so far removed from reality it makes no sense.
Selling $2,000 GPUs when you could sell $25,000 GPUs instead is what I would call charity, yes.

And I'm pretty sure that according to US laws, Jensen could be in trouble if his company provided much more gaming GPUs that it has. His investors could sue his *ss to Mars and back.

It's not the fact that you bought a GPU. It's the fact that this $2,000 GPU is available for sale in the first place.

And as I explained above, lower quality means greater stock and lower price.

But when people have that much comprehension impairment, it's a miracle we are only sinking at this slow pace. Jeez.
Posted on Reply
#382
Visible Noise
Good god, Nvidia mucked up good.
Hecate91Thank you for the clarification.
As you can tell I just don't have much of any trust left for Nvidia, after their doubling down on the power connector, and now trying to downplay missing ROPs, I wonder how Nvidia is actually going to fix this or are the AIBs going to be left dealing with customers.
And you also apparently have no faith in W1zzard either, posting that he would participate in some kind of coverup.
Posted on Reply
#383
notoperable
Mondays Jensen gonna tell everyone Its a design feature
Posted on Reply
#384
Carillon
MacZSelling $2,000 GPUs when you could sell $25,000 GPUs instead is what I would call charity, yes.

And I'm pretty sure that according to US laws, Jensen could be in trouble if his company provided much more gaming GPUs that it has. His investors could sue his *ss to Mars and back.

It's not the fact that you bought a GPU. It's the fact that this $2,000 GPU is available for sale in the first place.

And as I explained above, lower quality means greater stock and lower price.

But when people have that much comprehension impairment, it's a miracle we are only sinking at this slow pace. Jeez.
I think nvidia is not in the position to exit the gaming market, unlike amd and intel, nvidia has a monopoly on gaming, while on the datacenter side it has a gazillion competitors. All of it's customers hate them, and are designing their own gpus.
Posted on Reply
#385
MacZ
CarillonI think nvidia is not in the position to exit the gaming market, unlike amd and intel, nvidia has a monopoly on gaming, while on the datacenter side it has a gazillion competitors. All of it's customers hate them, and are designing their own gpus.
This doesn't change the fact that Data center are 78% of its revenue while gaming GPU are 17.1%.

And the trend is not in favor of gaming GPUs.

I don't think it will exit the gaming market, but as, any company would do, it will prioritize the segment that makes 4.5 times more revenue than the other (and growing).

I'm sorry to say that it is how things are.
Posted on Reply
#386
Hecate91
MacZSelling $2,000 GPUs when you could sell $25,000 GPUs instead is what I would call charity, yes.

And I'm pretty sure that according to US laws, Jensen could be in trouble if his company provided much more gaming GPUs that it has. His investors could sue his *ss to Mars and back.

It's not the fact that you bought a GPU. It's the fact that this $2,000 GPU is available for sale in the first place.

And as I explained above, lower quality means greater stock and lower price.

But when people have that much comprehension impairment, it's a miracle we are only sinking at this slow pace. Jeez.
It isn't a charity when Nvidia just cannot treat the gaming customers like crap, Nvidia is still invested in the gaming market and not caring about the gaming market is a dumb move as the AI bubble can pop, or the need for Nvidia for GPGPU as AI cards can diminish as many other companies are producing their own compute hardware.
Also according to US laws, Jensen could be in trouble for selling the AIBs cards with missing ROPs, he's already lied about the 5070 being faster than a 4090 when the 5070Ti doesn't even beat a 4090.
It doesn't matter what the GPU costs, to use the car analogy again, say you paid full price for a car it should be expected for the car to perform as advertised, not get a V6 vehicle only firing on 5 cylinders. There are laws against false advertisment and anti-consumer tactics.
And there is no excuse for lower quality chips, Nvidia had the choice to delay Blackwell to fix the quality issues.
I can comprehend your argument just fine, but your logic of praising Nvidia for selling defective hardware is a completely flawed argument.
Visible NoiseAnd you also apparently have no faith in W1zzard either, posting that he would participate in some kind of coverup.
To be honest I don't have trust in most reviewers with Nvidia cards, and every reviewer has to follow the rules or they no longer get cards or press guides.
For example, Hardware Unboxed tried calling out Nvidia, they nearly got blacklisted for it so HWUB changed to being significantly less critical of Nvidia.
Posted on Reply
#387
PerfectWave
Jensen say it is a features the more you buy more you save in ROPS LUL:roll:
Posted on Reply
#388
tfdsaf
All of those Nvidiots deserve it. $2500+ for what is essentially a 5080, just rebranded so that their stockhold syndrome slaves can make Jensen richer!

The 4080 historically would have been the 5070 and the 4090 the actual 4080, the 5090 would have historically been the 5080 or maybe 5080ti at best, not an actual $2500+ halo product. Every single Nvidia GPU in these past 2 generations is a scam!
Posted on Reply
#389
MacZ
Hecate91And there is no excuse for lower quality chips, Nvidia had the choice to delay Blackwell to fix the quality issues.
I can comprehend your argument just fine, but your logic of praising Nvidia for selling defective hardware is a completely flawed argument.
I'm not praising anyone or anything. I'm just explaining reality as I see it, however bleak it may seem.

Explaining is not condoning.

As I explained, I think that stricter quality controls would have resulted in less stock therefore even more expensive hardware.

And what would have been the reaction of the community then ?

If you think you have ground for suing nVidia, more power to you.
Posted on Reply
#390
Tek-Check
MacZI'm saying that you should be grateful to buy a $1,000 car when this company can sell $25,000 cars all day.
If you are not happy with the quality you get, you should stop buying the $1,000 car.
What kind of nonsense is this?
Posted on Reply
#391
MacZ
Tek-CheckWhat kind of nonsense is this?
Please explain what you find nonsensical.

Any for profit company in the world would rather sell a thing for $25,000 than for $1,000.

Where is the mystery ?
Posted on Reply
#392
Tek-Check
MacZAs I explained, I think that stricter quality controls would have resulted in less stock therefore even more expensive hardware.
No. This is flawed. Nvidia knew about defective dies and yet they waited until the community discovered it to make any statement.
Nobody forced them to announce cards at CES. It's their fault they rushed this non-launch with a handful of cards. I have not seen such disastrous paper launch with additional issues in a decade.
MacZAny for profit company in the world would rather sell a thing for $25,000 than for $1,000.
Which "thing"?
If they want to sell only data center GPUs, that's fine by me. Leave gaming market and sell what you want.
Posted on Reply
#393
MacZ
Tek-CheckNo. This is flawed. Nvidia knew about defective dies and yet they waited until the community discovered it to make any statement.
Nobody forced them to announce cards at CES. It's their fault they rushed this non-launch with a handful of cards. I have not seen such disastrous paper launch with additional issues in a decade.
Yes, I think they knew.
Yes, I think it's on purpose.

It is a choice between less quality and less quantity (and more expensive).

And quality always loses.

Look at the debacle with SMR hard drives.
Tek-CheckWhich "thing"?
If they want to sell only data center GPUs, that's fine by me. Leave gaming market and sell what you want.
Or you just don't buy nVidia cards. You are not alone. For some reason, some people want high end graphics cards whatever the price (almost). And there is no alternative to nVidia. So not everything is about you.
Posted on Reply
#395
MacZ
GodrillaYes it's illegal!
A full $1.3 millions ?

I'm sure Jensen at the head of its $3 trillions company will have a hard time sleeping.

Especially when you can RMA the faulty cards.
Posted on Reply
#396
JustBenching
Hecate91To be honest I don't have trust in most reviewers with Nvidia cards, and every reviewer has to follow the rules or they no longer get cards or press guides.
For example, Hardware Unboxed tried calling out Nvidia, they nearly got blacklisted for it so HWUB changed to being significantly less critical of Nvidia.
Hub changed to being significantly less critical of nvidia? The same hub that made 7 videos scrapping on nvidias 8gb vram cards (while at the time amd was also offering 8gb vram cards which they ignored mind you). We are talking about the same hub? Oh lord...
Posted on Reply
#397
Krit
The more you spend the harder you will fall.

- Poor performance
- High prices
- A lot of issues
- Worst nvidia gpu generation ever

When was the last time when nvidia had such bad times in general ?

I thought that RTX 40 Series was the worst but this one seems to be is even worse thanks to nvidia buyers.
Posted on Reply
#398
JustBenching
KritThe more you spend the harder you will fall.

- Poor performance
- High prices
- A lot of issues
- Worst nvidia gpu generation ever

What was the last time when nvidia had such bad times in general ?

I thought RTX 40 Series was the worst but this seems to be is even worse thanks to nvidia buyers.
Poor performance made me chuckle, not gonna lie. Poor performance... 6 fastest cards on raster performance are all nvidia. :banghead:
Posted on Reply
#399
Krit
JustBenchingPoor performance made me chuckle, not gonna lie. Poor performance... 6 fastest cards on raster are all nvidia. :banghead:
Just stop it or wake up! When looking at history in general (performance gains) RTX 50 Series on average are the weakest generation ever released.
Posted on Reply
#400
JustBenching
KritJust stop it or wake up! When looking at history in general (performance gains) RTX 50 Series are the weakest generation ever released.
Imagine how freaking terrible everyone else is doing on performance gains if they can't even get top 5 against these crappy nvidia cards. Insane, right?

2 crap nvidia generations in a row and instead of everyone else passing them by in performance, the gap gets larger and larger. Unfathomable...
Posted on Reply
Add your own comment
Feb 25th, 2025 12:54 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts