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.
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:
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:
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
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.
491 Comments on NVIDIA GeForce RTX 50 Cards Spotted with Missing ROPs, NVIDIA Confirms the Issue, Multiple Vendors Affected
I don't think you realize how much stuff actually is present on these chips, you're talking about millions/billions of data lines, you simply cannot test everything every time, it's not feasible. It's more reliable to check the GPU die first, detect the defects and configure the firmware.
melted power supply side connectors + melted cable + defective connector on the graphic card
+ possible fire hazard - which everyone denies in this forum.
150°C thermal pictures are enough to state that in certain cases = trouble.
We rely on the power supply unit, because the cable has no fuses and the graphic card has no fuses.
As of now - no mainboard, no nvme, no monitor was harmed (assumption).
I would be very upset when my M2 NVME would be dead because of the mainboard because of a nvidia 5090 graphic card and a asus power supply.
I would be very upset whne my floor would burn and all the furniture because of a nvidia graphic card, asus power supply unit and a cable.
Who wants to make an insurance for 0€ and take all nvidia card owners as insurance takers? I would not bet on that in the long run.
Still no power supply unit company had made any statements? Or am I wrong? There are two sides. The psu side and the nvidia 5090 side. This only takes in consideration normal usage - not abuse or special use like overclocking or other operation modes I have not even thought of.
All manufacturing has some issues, even if you work in much more critical industries, so reporting a problem with a single unit isn’t really news worthy. I wouldn’t really read any conspiracy into that - a single failure is just that.
Many times the reviewers also notice issues with the product, but when notifying the company they are told they have pre-production sample, and the issues should be fixed in retail, and such issues many times aren’t mentioned in reviews. I know some reviewers then don’t publish such reviews since they don’t represent the retail product, others don’t have issues with that.
I still couldn't find any info if these GPU dies are marked differently, that would clarify a lot of things.
So now your cards can burn due to “user error”, can face black screens or miss performance targets when you got lucky enough to get one anyway. That's an “epic” launch, but it still benefits the company and the other two are going to screw up again I suppose.....
Edit : by customer I mean the final one, not the system builder making the PC
Next driver version will stop reporting real active ROP numbers and just have a define with whatever the number is supposed to be, problem solved.
An entire new level of silicon lottery was just unlocked :D
Until yesterday, nobody noticed that ROPs were missing. When I found out I drafted the news post, informed Zotac, asked for a statement and published our story, nothing was held back.
Also @wNotyarD That won't work .. what about the missing performance?
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.
What they need to do to at least partly recover is as follows:
A. Reduce prices(a lot) to reflect the piss poor performance compared to previous gen cards.
B. Do away with the dangerous ATX3.0 power jack and bring back the PCIe jacks that are KNOWN to be safe and DON'T melt.
C. Offer replacements for cards that not at the declared specs.
D. Plan for a better future, one where they are honest, competent and fair.
@ NVidia
People, pull your heads out of your asses, get your shit together and quit being incompetent jerks! This showing is piss poor and unacceptable. You REALLY need to pull a GTX1000 series kind of run with RTX6000, in every respect, including performance/power/price ratio.
@ Jensen Huang
All of these circumstances clubbed together make you look like a liar. You claimed specific levels performance, RTX5000 has not delivered. You are either woefully out of touch with reality(likely given your comment about $10,000 PCs) or have lost grip of your senses & mental faculties entirely. Either way, get a grip or step down.
I think AMD and Intel really have a chance to close the gap here.. And yes folks I'm an NVidia guy. However I'm not a fanboy nor someone whose judgment is less than objective.
- consumer brainwashing by marketing that 5070 is "faster" than 4090
- MSRP means "Multiple $hitty Retail Prices"
- more users complain about black screen issue
- 600W power connector is still melting two years later, with no user error (DerBauer)
- no cards to be purchased anywhere in any meaningful volume
- PhysX 32-bit support ended ( list of affected games )
- defective chips with less ROPs that Nvidia knew about before shipping (legal issue?)
- a halo card catches random fire (not enough time for AIBs to test PCBs?)
Of course things could be different in this case, I have no official or inofficial information. Just sharing what's done usually
It can become a legal issue immediately if anyone tries to hide anything.
The gaming market is up for grabs. And I don't want to use that kinda sexist glengarry glenn ross line from Blake but.... it's that.
From my understanding, to have as much stock as possible, nVidia just allowed much more questionable quality than before.
These gaming GPUs are competing for wafer space with $25,000 AI GPUs that CEOs are having meeting with Jensen Huang to beg for having their order processed in a reasonable time.
People should be happy to have any at all, because they are in no way, shape or form entitled to any GPUs at any price point.
They are otherwise welcome to build their own GPU company. Ask the chinese for pointers, maybe.