Thursday, January 8th 2026

GeForce RTX 60-series Linked to Mysterious "GR20x" GPU Dies, 2H'27 Launch Predicted

A sizeable gap—not occupied by NVIDIA's heavily rumored, and possibly tenuous GeForce RTX 50 SUPER-series—has been noticed at this week's CES trade show. During kick-off hours, the North American giant's GeForce social media quietly declared that "no new GPUs will be announced" within the four-day-long event. Graphics card industry observers have seemingly become tired of pursuing mid-generation product refreshments, and have set their sights further along Team Green's timeline. Yesterday, kopite7kimi fielded a number of queries regarding a futuristic GeForce RTX 6000 graphics lineup. Logically, these next-gen designs could leverage "Rubin" GPU architecture—already previewed as a well-known property in enterprise fields.

Speculation from last September—hinging on NVIDIA's official unveiling of their "Rubin CPX" GPU, that sports CUDA cores—lead to a theory that "GR10x" dies would form the basis of truly next-wave gaming graphics cards. In early 2026, kopite7kimi has proposed the utilization of a different set of GPU dies—identified as the "GR20x" group (or "GR200" family). Specifically, the PC hardware sleuth has pinpointed an alleged "GR212" model. They surmise that NVIDIA's "Rubin" architecture-based GeForce RTX 60-series will arrive within a second half of 2027 launch window.
Sources: VideoCardz, Notebookcheck
Add your own comment

36 Comments on GeForce RTX 60-series Linked to Mysterious "GR20x" GPU Dies, 2H'27 Launch Predicted

#1
TumbleGeorge
Wonderful, almost 3 years between generations, without "super" series. At this rate, the 70* series will probably be launched in the next decade.:(
Posted on Reply
#2
TheinsanegamerN
TumbleGeorgeWonderful, almost 3 years between generations, without "super" series. At this rate, the 70* series will probably be launched in the next decade.:(
I mean, do we really need generations every 2 years? From a graphic perspective, even hardware from 6 years ago works perfectly fine, and based on Steam most gamers only upgrade every 3-4 generations anyway.

It just means we get longer lifespans from out current expensive processors. And said lifespans will also force developers to better optimize their products because they cant just count on ever increasing GPU power to cover up their work.
Posted on Reply
#3
TumbleGeorge
TheinsanegamerNAnd said lifespans will also force developers to better optimize their products because they cant just count on ever increasing GPU power to cover up their
Not sure about that.
Posted on Reply
#4
Hecate91
A 60 series would be even worse of a paper launch with more mythical MSRP's than the 50 series launch, unless the AI bubbles pops before 2027.

Game publishers aren't going to optimize games when they can just force you to use upscaling and 6X frame gen.
Posted on Reply
#5
LastDudeALive
TheinsanegamerNI mean, do we really need generations every 2 years? From a graphic perspective, even hardware from 6 years ago works perfectly fine, and based on Steam most gamers only upgrade every 3-4 generations anyway.

It just means we get longer lifespans from out current expensive processors. And said lifespans will also force developers to better optimize their products because they cant just count on ever increasing GPU power to cover up their work.
Also, it means that there will be better stock of RTX 60 available at launch. With Blackwell, Nvidia launched the enterprise and consumer products simultaneously, and they underestimated consumer demand. But now, they can reliably fulfil enterprise demand first, and then have the freedom to stock up a large supply of consumer chips later.

There's even the possibility of getting RTX 60 on a smaller node, maybe 2nm instead of the N3 nodes that Rubin is currently produced on.
Posted on Reply
#6
BorisDG
Extremely hyped for RTX 60. Should be next big generational leap. At least we will have new modern node.
Posted on Reply
#7
TheinsanegamerN
TumbleGeorgeNot sure about that.
Every time in history that hardware cadence has slowed down, developers have had to work within hardware restrictions. If GPU releases become a 3 year thing, developers are going to have to work with what is on the market.

If you game only works on the top 5% of GPUs, your market is naturally going to be only 5% of potential buyers.
Posted on Reply
#8
Antique4106
BorisDGExtremely hyped for RTX 60. Should be next big generational leap. At least we will have new modern node.
but at what cost..
Posted on Reply
#9
kondamin
If that means there will be significant gains other than frame gen, I guess that would be ok.
Them rereleasing the whole of 30xx at sane prices would probably be more meaningful for more gamers
Posted on Reply
#10
evernessince
TheinsanegamerNI mean, do we really need generations every 2 years? From a graphic perspective, even hardware from 6 years ago works perfectly fine, and based on Steam most gamers only upgrade every 3-4 generations anyway.

It just means we get longer lifespans from out current expensive processors. And said lifespans will also force developers to better optimize their products because they cant just count on ever increasing GPU power to cover up their work.
If decade of CPU market stagnation prior to Zen is anything to go by, Devs still won't optimize if you slow down the pace of improvement. They will simply release poorly optimized games or cut features.

Unreal Engine 5 in particular is a PITA to optimize for. It's a top-down engine, which means most features are enabled by default. It doesn't make it easy to pare down those feature either, even for someone like a senior technical artist. You basically have AA or better money to throw at the engine or you accept that ability to adjust the engine is going to be very limited. If unreal made it easier to ship lighter games, it wouldn't be seen is such a negative light.

There's also the issue that optimization doesn't sell video cards. Nvidia's style of "throw proprietary features into every game" won. They will obviously push features that sell GPUs, not optimizations that improve performance. Gamers voted with their wallets, or should I say against their wallets, once again. They really like doing that.
Posted on Reply
#11
Antique4106
kondaminIf that means there will be significant gains other than frame gen, I guess that would be ok.
Them rereleasing the whole of 30xx at sane prices would probably be more meaningful for more gamers
imagine a 4600 series, with the horsepower of the 50 series, just lacking the more advanced ai components. probably still wouldn't be optimal, but it would be nice to get a card without paying the ai tax for features i'll never use
Posted on Reply
#12
TheinsanegamerN
evernessinceIf decade of CPU market stagnation prior to Zen is anything to go by, Devs still won't optimize if you slow down the pace of improvement. They will simply release poorly optimized games or cut features.

Unreal Engine 5 in particular is a PITA to optimize for. It's a top-down engine, which means most features are enabled by default. It doesn't make it easy to pare down those feature either, even for someone like a senior technical artist. You basically have AA or better money to throw at the engine or you accept that ability to adjust the engine is going to be very limited. If unreal made it easier to ship lighter games, it wouldn't be seen is such a negative light.

There's also the issue that optimization doesn't sell video cards. Nvidia's style of "throw proprietary features into every game" won. They will obviously push features that sell GPUs, not optimizations that improve performance. Gamers voted with their wallets, or should I say against their wallets, once again. They really like doing that.
You mean the decade where new games were playable on 10 year old hardware, thus proving my point? that decade?
Posted on Reply
#13
Hecate91
TheinsanegamerNYou mean the decade where new games were playable on 10 year old hardware, thus proving my point? that decade?
The decade when new games were playable on 10 year old hardware, because game devs were using in house engines, weren't pushing features that required high end hardware, and GPU makers were providing a significant performance uplift with every new gen instead of selling upscaling and frame gen as an improvement.
Posted on Reply
#14
kondamin
Antique4106imagine a 4600 series, with the horsepower of the 50 series, just lacking the more advanced ai components. probably still wouldn't be optimal, but it would be nice to get a card without paying the ai tax for features i'll never use
Yeah, if they just launch something affordable that isn't on tsmc using the most expensive of memories that would be just great
Posted on Reply
#15
bug
I used to be an enthusiast since the early S3 2D acceleration solutions, but I just don't give a rat's @$$ anymore. Prices are a joke. Availability even a more cruel one.
Posted on Reply
#16
TumbleGeorge
There can be a big difference between playable and enjoyable. I've seen the minimum requirements for some games recently and they don't require particularly new hardware. But they do require 16GB RAM 8GB VRAM for 1080@30 and 32GB RAM and 12GB VRAM for 1080@60 FPS... I don't even want to guess what it requires for 1440P&4K Ultra. Check out 007 First Light...
Posted on Reply
#17
TechpowerLeft
TumbleGeorgeWonderful, almost 3 years between generations, without "super" series. At this rate, the 70* series will probably be launched in the next decade.:(
Sadly, the hardware evolution slowed down.
Considering this, 3 years aren't a shocking time interval.
Posted on Reply
#18
bug
TechpowerLeftSadly, the hardware evolution slowed down.
Considering this, 3 years aren't a shocking time interval.
I don't think the hardware slowing down is the primary factor here. I think the bidding for fab capacity is.
Of course, when it comes to Nvidia, the fact that other segments are more profitable for than then gaming, doesn't help.
Posted on Reply
#19
Onasi
TheinsanegamerNYou mean the decade where new games were playable on 10 year old hardware, thus proving my point? that decade?
Case in point, I sat on a 2600K since 2011 till 2021. The only thing that I have replaced in that time period were GPUs (570 to 770 to 1070). It really didn’t feel like the hit was massive in anything that wasn’t single-thread locked, like MMOs, but even then performance was mostly acceptable. If GPUs stagnate, the same things will happen. I don’t really know why people cite unoptimized UE5 junk as an example of the opposite - it’s just shit worksmanship, akin to terrible ports of old. They were always around and, unfortunately, will continue to be. The developers that will stubbornly refuse to learn their tools and continue to release shit that needs halo-tier cards just to perform at a baseline will lose market. We are already hearing rumblings of AAA industry being unhealthy and sales dropping.
Posted on Reply
#20
kondamin
bugI don't think the hardware slowing down is the primary factor here. I think the bidding for fab capacity is.
Of course, when it comes to Nvidia, the fact that other segments are more profitable for than then gaming, doesn't help.
Nah it's; Hardware evolution is slowing down.
Density increases are decreasing per node.
After 2nm nvidia will have to start making smaller chips and work with chiplets like intel and amd are doing for their cpu's.

it's not all that unlikely the 5090 will be the final seriously big die "consumer" gpu, they won't be bothering with cowos for gaming.
Posted on Reply
#21
Gucky
TumbleGeorgeWonderful, almost 3 years between generations, without "super" series. At this rate, the 70* series will probably be launched in the next decade.:(
Do you want to buy a GPU every year?
I don't case if it takes 3 or 4 years IF the jump is big enough. 15-20% per year seems doable.

And TSMC also can't do magic, they need time to shrink transistors. And that will take longer and longer or well.. more money.
Posted on Reply
#22
Hyderz
is this the one where nvidia say it move heavily away from rasterization and into neural rendering?
Posted on Reply
#23
N/A
Not a 6090 if FP64 (1:2), 6090 FP64 (1:64), if it focuses on FP4 as a selling point, then FP64 could be crippled. So it ends up being a bit smaller about the same size as the 5090.. 33% more CUDA and cache on the N3 that provides 30% better density,
Posted on Reply
#24
N3utro
TumbleGeorgeThere can be a big difference between playable and enjoyable. I've seen the minimum requirements for some games recently and they don't require particularly new hardware. But they do require 16GB RAM 8GB VRAM for 1080@30 and 32GB RAM and 12GB VRAM for 1080@60 FPS... I don't even want to guess what it requires for 1440P&4K Ultra. Check out 007 First Light...
This is either a mistake either there is a serious optimization issue with their game engine.

Games like cyberpunk and indiana jones and the great circle use around 12GB of ram maxed out at 1080p.

Gameplay footage from 007 first light show that its graphics and map sizes dont appear to be anything close to these 2 games, so there is no reason that it would require 3 times more ram.
Posted on Reply
#25
Bwaze
I bet you really have to draw the short straw in Nvidia to be put on developing consumer products now - when all the focus is on AI servers, and delays, shortages and cancellations in consumer sector somehow even signal how the times have changed, revenue and focus is elsewhere. I think second half of 2027 is now so far we could see entire PC sector cave in before that.

This now is wholly unprecedented, and memory price increases have nothing in common with price increases during cryptoinsanities - during crypto surges, when gamers couldn’t get any graphics card at normal price, most of the PC sector wasn’t really affected - most work, home computers are sold without dedicated graphics card, and more importantly, GPUs were still sold, although not for gaming.
Posted on Reply
Add your own comment
Nov 18th, 2026 13:52 CST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts