Saturday, October 10th 2026

NVIDIA Reportedly Ending the RTX 5090, Reserves GB202 Silicon for Workstation GPUs

NVIDIA has reportedly stopped allocating GB202 silicon to the GeForce RTX 5090, according to leaker MEGAsizeGPU (@Zed__Wang) on X. "No more GB202 for 5090, confirmed," the leaker posted, adding in a follow-up that "all future GB202 supplies are RTX Pro exclusive." GB202 is the largest "Blackwell" graphics chip, and the RTX 5090 doesn't even max it out. The same chip powers the 96 GB RTX PRO 6000 with 24,064 CUDA cores, as well as the recently unveiled RTX PRO 5500, which pairs the RTX 5090's 21,760 CUDA cores with 84 GB of memory. Apparently, NVIDIA would rather put every GB202 it gets into those far pricier workstation cards. The company hasn't confirmed any of this as of the time of writing.

A second leaker, hongxing2020, posted "5090 EOL, 5080 24GB ready" alongside an apparent factory notice saying NVIDIA will no longer sell any RTX 5090 model, China-market D variants included. The same notice says an RTX 5080 24 GB will become the top GeForce card and the 16 GB version will be discontinued. That sounds a lot like the RTX 5080 SUPER, which was rumored with 24 GB of GDDR7 on the same GB203 chip, although it isn't clear if the two are the same card. SUPER cards reportedly reached board partners in July, only to be put on hold over GDDR7 pricing. As for the RTX 5090, I doubt NVIDIA would formally call this an end-of-life (EOL) move, since the chips are simply being redirected to a more profitable product line.
RTX 5090 buyers were already having a rough time. The card launched in January 2025 at $1,999, and last month European listings went past €5,000 while Walmart sold out at $4,299. Cards built from GB202 chips that partners already have could keep trickling out for a while, though it's reasonable to expect prices to climb further once that stock dries up. Of course, the RTX 5090 was hardly a gaming card for most people by this point, with AI firms reportedly picking up stock in bulk before it ever reached gaming retail. With the RTX 60-series reportedly slipping to 2028, the RTX 5080 24 GB may stay the fastest GeForce card in production for a long time.
Sources: MEGAsizeGPU on X, hongxing2020 on X, via Videocardz
Add your own comment

228 Comments on NVIDIA Reportedly Ending the RTX 5090, Reserves GB202 Silicon for Workstation GPUs

#51
SOAREVERSOR
wheresmycarSo business as usual!

In terms of raw performance, things aren't looking good for higher resolution gaming.... certainly not for the foreseeable future. We’ve entered an era defined by feature sets rather than raw performance.

We get it, RTX PRO cards are more profitable but I wonder how much of this is also down to the 5090's power connector issues + RMAs. Or are the 600W RTX PRO cards facing similar problems?
The power connector problem is almost entirely constrained to the PC DIY gaming crowd. I've installed 5090s in bulk for business consumers and not had a problem. It's the DIY group that's having them with the exact same cards. OEMs shipping cards with the power connector are also not seeing problems outside of the usual rate.

The high rate is strictly with the DIY gaming crowd. Which shows you who's to blame. Let's face it building a PC takes no skill now compared to what it used to. There's no way around that. So there are a lot of people building gaming PCs now that have no business building them as they do not know what they are doing. Those who grew up with molex, IDE, floppy, SCSI, jumpers for all sorts of nonsense do not have these problems.

There's no need for nvidia to fix this because it's not happening where most of these get installed in abnormal numbers. It's not happening at the extremes people here claim if you buy a Dell gaming computer or even a custom one from say Digital Storm. It's sure as hell not happening with the Pro cards. Where it is going wild is a bunch of DIY gamers running into it and that firmly shows there are a lot gamers building computers who should not be. That's not on nvidia. This doesn't even rate in the long history of ways people have screwed up DIY builds it's a blip.

Since PC gaming is moving to the cloud or local APUs and nothing can change that there is no reason for nvidia to care about people botching something that had no business trying. The people installing this will all know what they are doing and the people who don't won't really be able to buy one. If you are worried about the power connector now simply don't build your computer yourself. Dude you're gettings a Dell! Part of the markup with premades is the lengthy testing and validation process along with skilled technichians. Most DIY gamers are not capable of doing this and wouldn't even know how. The card should have never been released to the DIY crowd at all. Hopefully nvidia learns their lesson going forward and removes the DIY market for their top options.
Posted on Reply
#52
AVATARAT
LuminescenttCrazy how you read this post and immediately went, “AMD lol.”

Nvidia has the market dominance to charge whatever they want for GPUs, melting power cables, and increasingly anti-consumer pricing, yet some of you will defend them no matter what. The level of bootlicking is insane. Some of you disguise yourselves as intellectual, unbiased tech enthusiasts on these forums, but in reality you’re just mindless cattle defending a corporation that couldn’t care less about you.
A tech enthusiast uses every graphics card he can afford. He just hates them—
he probably had a bad experience with AMD 15 years ago and couldn't forget it.
Posted on Reply
#53
Godrilla
HappyguynpcI don't want to be someone who wishes harm, but I think that soon, with quantum computing or some new AI technology will make processing AI models easier, and Nvidia will sink into a crisis
New current trend in ai or llms putting signature on results and reverse engineering older software via vibe coding like exclusive games into emulators. The next evolution is naturally quantum level encryption for data protection. Imo quantum stocks will eventually be where Ai stocks are today. Everyone will have a subscription to quantum especially the big whales to security.
Posted on Reply
#54
TheinsanegamerN
Good. All gamers have done is whine and cry and scream about how evil nvidia is and how bad the connectors are and how bad the cards are and how huang is evil and how nvidia hates gamers and yadda yadda yadda. Everyone was filling their diapers wailing about "Oh NvIdIa HaS aBaNdOnEd GaMeRz WaAaAaAaAa NoBoDy CaN aFfFoRd GpUs wHeRe Is My $500 5090 WaAaAaAaAh!" for half a year, then when nvidia stops allocating the 5090 nobody can afford, we have to wail AGAIN about how evil nvidia is and how everythign is over and blah blah blah yadda yadda yadda.

Nvidia should go further. Get rid of everything above the 5050. Gamers dont deserve anything above that. Wouldn't want them melting any cables, now would we?
Posted on Reply
#55
AusWolf
SOAREVERSORThe power connector problem is almost entirely constrained to the PC DIY gaming crowd. I've installed 5090s in bulk for business consumers and not had a problem. It's the DIY group that's having them with the exact same cards. OEMs shipping cards with the power connector are also not seeing problems outside of the usual rate.

The high rate is strictly with the DIY gaming crowd. Which shows you who's to blame. Let's face it building a PC takes no skill now compared to what it used to. There's no way around that. So there are a lot of people building gaming PCs now that have no business building them as they do not know what they are doing. Those who grew up with molex, IDE, floppy, SCSI, jumpers for all sorts of nonsense do not have these problems.
What special magic power connector plugging skill do experienced PC builders possess that new builders don't? Or is the power connector so smart that it knows whether it was plugged in by a seasoned enthusiast or someone else?
SOAREVERSORSince PC gaming is moving to the cloud or local APUs
Gaming has been "moving to the cloud" for the last 10 years, yet, nothing has come of it.
TheinsanegamerNGood. All gamers have done is whine and cry and scream about how evil nvidia is and how bad the connectors are and how bad the cards are and how huang is evil and how nvidia hates gamers and yadda yadda yadda. Everyone was filling their diapers wailing about "Oh NvIdIa HaS aBaNdOnEd GaMeRz WaAaAaAaAa NoBoDy CaN aFfFoRd GpUs wHeRe Is My $500 5090 WaAaAaAaAh!" for half a year, then when nvidia stops allocating the 5090 nobody can afford, we have to wail AGAIN about how evil nvidia is and how everythign is over and blah blah blah yadda yadda yadda.

Nvidia should go further. Get rid of everything above the 5050. Gamers dont deserve anything above that. Wouldn't want them melting any cables, now would we?
So we have to "deserve" graphics cards now? How? Paying for them isn't enough anymore?
Posted on Reply
#56
Youseethis
AusWolfSo we have to "deserve" graphics cards now? How? Paying for them isn't enough anymore?
I think the caustic sarcasm insinuates that as long gamers do not vote with their wallets nothing would change and they will continue to loose ground as more and more dies end up towards professional use. The complaints are meaningless.

To be fair there is no voting with your wallet when your opponent is 10x richer. (gaming vs datacenter revenue). Right now they will gobble up everything and anything.

Only gb207 will remain :roll:
AusWolfGaming has been "moving to the cloud" for the last 10 years, yet, nothing has come of it.
And thankfully never will, the speed of light is the limit in many cases.
Posted on Reply
#57
AusWolf
YouseethisI think the caustic sarcasm insinuates that as long gamers do not vote with their wallets nothing would change and they will continue to loose ground as more and more dies end up towards professional use. The complaints are meaningless.

To be fair there is no voting with your wallet when your opponent is 10x richer. (gaming vs datacenter revenue). Right now they will gobble up everything and anything.

Only gb207 will remain :roll:
Ah I see. That makes sense. :)
YouseethisAnd thankfully never will, the speed of light is the limit in many cases.
Agreed.
Posted on Reply
#58
XeonsNOpterons
lepudrukOk... If someone thought the 5090s were expensive, just wait and see - prices will shoot to the moon at the speed of light. Damn, I'm really glad I managed to buy mine for €3000.
If this rumor is true, it is insane we are losing the flagship tier from Nvidia. RDNA5 may indeed be the king then if the AT0 die is as big as claimed. I was not going to be able to afford the RTX 5090 before the crazy price rise, let alone now. Do not really need it anyways for my work, but still a shock to see the flagships may be gone from Nvidia.
Posted on Reply
#59
Youseethis
XeonsNOpteronsIf this rumor is true, it is insane we are losing the flagship tier from Nvidia. RDNA5 may indeed be the king then if the AT0 die is as big as claimed. I was not going to be able to afford the RTX 5090 before the crazy price rise, let alone now. Do not really need it anyways for my work, but still a shock to see the flagships may be gone from Nvidia.
Why would you assume that at0 will not have the same fate as gb202? :roll:
Posted on Reply
#60
AusWolf
XeonsNOpteronsIf this rumor is true, it is insane we are losing the flagship tier from Nvidia. RDNA5 may indeed be the king then if the AT0 die is as big as claimed. I was not going to be able to afford the RTX 5090 before the crazy price rise, let alone now. Do not really need it anyways for my work, but still a shock to see the flagships may be gone from Nvidia.
And to continue that logic, what I've been saying for a long time will prove itself: market share doesn't matter. AMD and Nvidia are both filthy rich, whether they own 5, 20, or 90 percent of the (gaming) market is inconsequential.
Posted on Reply
#61
XeonsNOpterons
YouseethisWhy would you assume that at0 will not have the same fate as gb202? :roll:
Don't make me despair more lol
AusWolfAnd to continue that logic, what I've been saying for a long time will prove itself: market share doesn't matter. AMD and Nvidia are both filthy rich, whether they own 5, 20, or 90 percent of the (gaming) market is inconsequential.
Yep, it is all just insanity for more money they will never spend on yachts or R&D.
Posted on Reply
#62
TheinsanegamerN
XeonsNOpteronsYep, it is all just insanity for more money they will never spend on yachts or R&D.
See, this is the kind of thing I was talking about. It's demonstrably wrong, every tech company in the space spends exponentially more on R+D now then they did a decade ago, and those numbers are not going down. Node costs continue to rise above the rate of inflation, hundreds of billions are being spent on new production facilities, and transportation costs have skyrocketed due to fuel and tariff and wage prices.

And frankly, AI is a very useful tool. It's not a human replacement, but its capabilities are very impressive for what it can do, which can be readily seen in content creation and the coding space. Just look at game recompilations that are getting churned out now VS the rare release of a few years ago.

It's not "insanity", it is economics 101. That money is not being collected like Smaug's gold, it is being burnt, at insane speeds, to push what is seen as the new tech revolution.
Posted on Reply
#63
BoggledBeagle
Solid State BrainI imagine something like $1399 MSRP at the minimum.
1400 seems very optimistic to me, and also MSRP seem irrelevant nowadays.

A place vacated by a 5090 could be filled with 24GB 5080, including the price. 5070 Ti now cost what 5080 used to cost anyway.
Posted on Reply
#64
Frick
Fishfaced Nincompoop
HappyguynpcI don't want to be someone who wishes harm, but I think that soon, with quantum computing or some new AI technology will make processing AI models easier, and Nvidia will sink into a crisis
1) Quantum computing is so far away from whatever Nvidia is doing it's an entirely different industry, and 2)
Dr. DroNvidia is actively involved in the development of said tech.
This. What will sink Nvidia is when the AI bubble burst. Dro also mentions Nvidia will "move on" which ... sure, they could do other things, but not as a trillion USD entity that is involved in literally every aspect of economic growth.
Posted on Reply
#65
Solid State Brain
BoggledBeagle1400 seems very optimistic to me, and also MSRP seem irrelevant nowadays.

A place vacated by a 5090 could be filled with 24GB 5080, including the price. 5070 Ti now cost what 5080 used to cost anyway.
For comparison, these are MSRPs for the rest of the lineup, still listed on the NVidia website (scroll down):

5060 8GB ... $299
5060 TI 12GB ... $379
5060 TI 16GB ... $429
5070 12GB ... $579
5070 TI 16GB ... $749
5080 16GB ... $999

Of course they don't include scarcity-driven markup.
Posted on Reply
#66
john_
The whole situation reminds me a bit of the Titan series, though under completely different circumstances. Nvidia launched the Titan line back then specifically to condition the public into accepting $1,000 graphics cards. In some marketing campaigns, they promoted it as a semi-pro card—which had some justification given the distinct driver branch—thus legitimizing its price tag; in other ads, however, they pitched it as the ultimate gaming GPU for the PC enthusiast. Anyone buying a Titan purely for gaming was essentially playing right into Nvidia's marketing playbook.

Fast forward to today, and AI has taken a pure gaming card—packaged with gaming drivers and promoted across every Nvidia ad as a gaming GPU—and transformed it into a semi-pro AI card, except without dedicated AI-specific drivers. Its price went from sky-high to absurdly astronomical, which didn't stop people from buying it, since it wasn't just its own price going up, but the price of every Nvidia card across the board. The RTX 5090 would have never reached the price point it did if the prices of Pro models hadn't risen in tandem. Nvidia played the game brilliantly here, hiking prices without facing any real pushback from consumers. Instead, we sit around justifying situations that we'll end up paying for out of our own pockets tomorrow. Because Microsoft, Meta, and OpenAI are dumping insane money into GPUs, it's apparently considered reasonable to expect an average person earning 2–3 grand a month (or less) to fork over $1,000 tomorrow for an RTX 6070—if it even comes with a bare-minimum 16GB VRAM—and feel lucky on top of it if they later see that card's price climb past $1,500.

While I acknowledge that current market conditions make it unrealistic to expect better treatment from companies like Nvidia—especially when we actively defend their price hikes—I believe the absolute bare minimum we should do as consumers is to insist on treating the RTX 5090 in our discussions as a gaming card and nothing more. The moment we start telling each other "the RTX 5090 isn't just a gaming GPU," we hand Nvidia, AMD, or anyone else the green light to price their future mainstream models not as gaming hardware, but as semi-pro gear, despite shipping them exclusively with consumer gaming drivers.

As far as I'm concerned, the RTX 5090 remains an overpriced gaming card that didn't justify even its $2,000 MSRP. If you want to call it an AI card, you'd better start saving up—a lot—for your next upgrade right now.
Posted on Reply
#67
TheinsanegamerN
FrickThis. What will sink Nvidia is when the AI bubble burst. Dro also mentions Nvidia will "move on" which ... sure, they could do other things, but not as a trillion USD entity that is involved in literally every aspect of economic growth.
nvidia had over a trillion in market cap in 2023, before the AI craze. Outside of gaming, nvidia has their fingers in the automotive automation game, all the other datacenter focused production tasks like render farms and number crunchers, and even when the bubble "bursts", AI is still going to be a very valuable enterprise that will need new GPUs.

nVidia will survive just fine.
john_While I acknowledge that current market conditions make it unrealistic to expect better treatment from companies like Nvidia—especially when we actively defend their price hikes—I believe the absolute bare minimum we should do as consumers is to insist on treating the RTX 5090 in our discussions as a gaming card and nothing more. The moment we start telling each other "the RTX 5090 isn't just a gaming GPU," we hand Nvidia, AMD, or anyone else the green light to price their future mainstream models not as gaming hardware, but as semi-pro gear, despite shipping them exclusively with consumer gaming drivers.
So we need to live in an active delusion in the blind hope that it will make 5090s reappear? Are we manifesting more DDR7 for nvidia to use to bring prices down?

The 5090 is not a pure gaming card. IT can do other things, as can the rest of the lineup. Denying that to live in a fantasy world only leads one to become completely unhinged from reality.
Posted on Reply
#68
XeonsNOpterons
TheinsanegamerNSee, this is the kind of thing I was talking about. It's demonstrably wrong, every tech company in the space spends exponentially more on R+D now then they did a decade ago, and those numbers are not going down. Node costs continue to rise above the rate of inflation, hundreds of billions are being spent on new production facilities, and transportation costs have skyrocketed due to fuel and tariff and wage prices.

And frankly, AI is a very useful tool. It's not a human replacement, but its capabilities are very impressive for what it can do, which can be readily seen in content creation and the coding space. Just look at game recompilations that are getting churned out now VS the rare release of a few years ago.

It's not "insanity", it is economics 101. That money is not being collected like Smaug's gold, it is being burnt, at insane speeds, to push what is seen as the new tech revolution.
Ok, Bezos
Posted on Reply
#69
TheinsanegamerN
XeonsNOpteronsOk, Bezos
You cant refute anything so you resort to ad hominem attacks? Neat.
Posted on Reply
#70
Wasteland
ThomasKOther than that, it’s easy to realize that most of the GB202 supply is being bought for $5K by AI companies anyway, so in Nvidia’s consumer-friendly eyes, it’s much more profitable to ship that same silicon on a workstation GPU and charge even more for it, to the same customer.
Yeah, this story is a bit of a nothingburger from where I'm sitting. Almost no one was buying this card for $6k to play games. I don't have a ton of sympathy for the people who buy 5090s by the pallet to run AI workloads; if I were Nvidia, I'd make this move too, make them pay enterprise prices.

There are plenty of things for hardware enthusiasts to complain about in our current environment, many of them caused or exacerbated by Nvidia (along with a whole crowd of others, including AMD), but "oh no, this already unaffordable GPU that was effectively reserved for enterprise use cases will no longer be available to gamers" isn't exactly high on the list. What we're discussing is an insignificant symptom of a much larger trend.

The 5090 simply has too much VRAM NOT to be hoovered up for AI workloads. That's the world we live in. Maybe Nvidia will release a slightly weaker chip with less VRAM for the "gamers" at some point. Personally I don't think there are any triple-A games good enough to justify a halo-class GPU, these days, even given an infinite budget. YMMV.
Posted on Reply
#71
rusty caterpillar
phintsAt the price they're going for who cares. Release a $799 RTX 6070Ti on TSMC 3N (or better yet 2N) and I'm good.
More like 1200$++
Posted on Reply
#72
Frick
Fishfaced Nincompoop
TheinsanegamerNnvidia had over a trillion in market cap in 2023, before the AI craze. Outside of gaming, nvidia has their fingers in the automotive automation game, all the other datacenter focused production tasks like render farms and number crunchers, and even when the bubble "bursts", AI is still going to be a very valuable enterprise that will need new GPUs.
AI has supplemented all of that. Literally all of it. "Automation, datacenter", that is entirely AI now. And the current position of the people with stakes in AI is not that it's going to be a "very valuable enterprise", their position is that it's so powerful/game changing there's literally a chance human civilization will collapse because of it's awesome power. That is the level of hype Nvidia is cashing in on currently. A huge chunk of the world economic growth is tied to AI (and when it comes to some nations, it's all of it); when that comes crashing down there will not be such a thing as trillion dollar companies.
Posted on Reply
#73
BoggledBeagle
My honest opinion is that 99% of people do not REALLY NEED anything more powerful than a 5070 Ti to run games. I am talking about a real need here, not about wants caused by various external influences and pressures.
Posted on Reply
#74
Frick
Fishfaced Nincompoop
BoggledBeagleMy honest opinion is that 99% of people do not REALLY NEED anything more powerful than a 5070 Ti to run games. I am talking about a real need here, not about wants caused by various external influences and pressures.
This is a nonsensical point. To quote myself, "Our entire hobby could not exist outside times of extreme abundance". The only thing a human needs is water, food and shelter, and maybe companionship as a fourth place.
Posted on Reply
#75
Solid State Brain
BoggledBeagleMy honest opinion is that 99% of people do not REALLY NEED anything more powerful than a 5070 Ti to run games. I am talking about a real need here, not about wants caused by various external influences and pressures.
I purchased an RTX3090 24GB in early 2023 because I wanted to play around with local LLMs and image models and only secondarily run games in 4k resolution.
Most of my "gaming" with it so far has been AI models.
Posted on Reply
Add your own comment
Nov 12th, 2026 06:33 PST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts