RTX 5090, RTX 5080 Laptop GPUs Leak Alongside ASUS ROG Gaming Laptops

[GGforever]

It is barely a surprise that the desktop RTX 50X0-series cards will be accompanied by laptop variants soon after their launch. And as such, multiple listings of upcoming gaming laptops have appeared on the internet. The information is rather intriguing, to say the least. The leaked listings indicate that both AMD and Intel will have products ready to join forces with Blackwell, with Intel's Arrow Lake-HX and, rather shockingly, Ryzen 7000HX-series from Team Red - much to the chagrin of those expecting Ryzen 9000HX to drop sooner. The listings also reveal some other specifications, such as the display, but there is nothing notable there - it's the typical spread of mini LED and OLED panels.

Among the leaked laptops, we have the ROG Strix Scar 18, which will pack up to a Core Ultra 9 285HX "Arrow Lake-HX" CPU, along with either an RTX 5080, or an RTX 5090 GPU. Disappointingly, it appears that the RTX 5090 will be limited to only 16 GB of VRAM, which is half that of its desktop counterpart. The RTX 5080 will also be available with 16 GB of VRAM, which certainly makes us sigh in relief. A lower-tier laptop, namely the Strix 16, has also been leaked, packing either an RTX 5070 Ti, or an RTX 5060 GPU with 12 GB and 8 GB of VRAM respectively. The laptops further down will also have the entry-level RTX 5050, with 8 GB of VRAM as well. Of course, all of this is on the new GDDR7 spec. The full-resolution image of the leaked listings can be found here.



View at TechPowerUp Main Site | Source

 

[Upgrayedd]

How misleading is it to call two parts the same name when they aren't the same?

Didn't they used to put a "m" on mobile GPUs to just KIND of let knowledgeable users know that its not the same as the desktop part. They try to hide it now?

 

[Vya Domus]

Didn't they used to put a "m" on mobile GPU

Yes but that was just too honest of them, they eventually came to their senses and got rid of it.

They got rid of it back with 900 series when they released a "desktop" GTX 980 for laptops which was in fact a fully enabled GPU though of course it ran at lower clocks, ever since then they got rid of the "M" even though the actual GPU dies went back to being different from the desktop ones. Classic Nvidia move.

 

[Neo_Morpheus]

How misleading is it to call two parts the same name when they aren't the same?

Didn't they used to put a "m" on mobile GPUs to just KIND of let knowledgeable users know that its not the same as the desktop part. They try to hide it now?

That was back when they didnt get free passes like they do now.

Today, they can get away with murder and people will not only defend them but will pay for their lawyers.

 

[axiumone]

Wasn't there one generation where desktop and laptop parts had the same designation and were the same chip with nearly equivalent performance? Now we're back to this, where the model numbers are completely made up and meaningless.

 

[Solaris17]

Yes but that was just too honest of them, they eventually came to their senses and got rid of it.

They got rid of it back with 900 series when they released a "desktop" GTX 980 for laptops which was in fact a fully enabled GPU though of course it ran at lower clocks, ever since then they got rid of the "M" even though the actual GPU dies went back to being different from the desktop ones. Classic Nvidia move.

Let’s not forget not only are they cut down again but manufacturers will put them in chic laptops and they will run like absolute garbage and overheat just like the last gen’s.

poor @unclewebb

“My %CPU% and Nvidia 50x0 on my %manufacturer% 14” dynasty edition 4mm thick magnesium body gets soft during extended gameplay and reaches 400c, what settings do I use in TS to get 900fps and no performance degradation?” -Thanks

 

[Space Lynx]

Let’s not forget not only are they cut down again but manufacturers will put them in chic laptops and they will run like absolute garbage and overheat just like the last gen’s.

poor @unclewebb

“My %CPU% and Nvidia 50x0 on my %manufacturer% 14” dynasty edition 4mm thick magnesium body gets soft during extended gameplay and reaches 400c, what settings do I use in TS to get 900fps and no performance degradation?” -Thanks

The sad part it, if they would just make them 1/2 inch thicker, and do some innovative cooling (also not cheap out), we could have a really nice gaming laptop that stays cool. I think 1920x1200 OLED high refresh, should be the maximum resolution for any laptop size, the pixel density makes it perfectly fine.


Also, cpu clocked super high doesn't really seem to matter for a lot of games, so a 45w or even 35w cpu, combined with a 140w or 120w dedicated gpu could go a long way. It's just so sad they feel the need to constantly bungle laptop design.

 

[TheinsanegamerN]

Wasn't there one generation where desktop and laptop parts had the same designation and were the same chip with nearly equivalent performance? Now we're back to this, where the model numbers are completely made up and meaningless.

Yes, that was maxwell. They were not identical but they were close and the 980 did have a full fledged mobile part.

For whatever reason Nvidia got real conservative with hose core designs.

 

[Cheeseball]

Yes, that was maxwell. They were not identical but they were close and the 980 did have a full fledged mobile part.

For whatever reason Nvidia got real conservative with hose core designs.

Turing (RTX 2000) as well. I had a RTX 2070 laptop before and it had the 2304 shaders/64 ROPs like the desktop variant, with just the TGP cut down to 115W compared to 175W.

2080 Super Mobile was 150W TGP and the desktop version was 250W. Same TU104.

 

[solarmystic]

Wasn't there one generation where desktop and laptop parts had the same designation and were the same chip with nearly equivalent performance? Now we're back to this, where the model numbers are completely made up and meaningless.

It was Pascal, the golden generation where both laptop and desktop variants used the exact same die for all parts and the performance delta between both weren't that far apart. Hell, some mobile variants like GTX 1070 mobile had MORE cores.

Eg:-

GTX 1050TI = GTX 1050TI mobile = 768 cuda cores
GTX 1060 = GTX 1060 mobile = 1280 cuda cores
GTX 1070 = 1920 cuda cores, GTX 1070 mobile = 2048 cores
GTX 1080 = GTX 1080 mobile = 2560 cuda cores

Turing kept the same die between mobile and desktop but mobile variants were severely downclocked to have reasonable TDP limits.

From Ampere onwards, they had different designations again.

 

[iuliug]

I told someone interested in buying a 40 series mobile GPU that the laptop version was 70% slower than the desktop one. Was shocked- still gonna buy.

 

[arestavo]

Only 8GB of VRAM on a mobile 5070? OUCH.

 

[Ruru]

It was Pascal, the golden generation where both laptop and desktop variants used the exact same die for all parts and the performance delta between both weren't that far apart. Hell, some mobile variants like GTX 1070 mobile had MORE cores.

Eg:-

GTX 1050TI = GTX 1050TI mobile = 768 cuda cores
GTX 1060 = GTX 1060 mobile = 1280 cuda cores
GTX 1070 = 1920 cuda cores, GTX 1070 mobile = 2048 cores
GTX 1080 = GTX 1080 mobile = 2560 cuda cores

Turing kept the same die between mobile and and desktop but mobile variants were severely downclocked to have reasonable TDP limits.

From Ampere onwards, they had different designations again.

The 1070 mobile was indeed interesting as it had more shaders than the desktop version. Wonder that are there any weird Frankenstein cards using the 2048-shader die in a desktop card.

 

[Nhonho]

Has Nvidia already published the date the embargo on specifications and reviews for the RTX 5000 ends?

 

[unwind-protect]

I also spend considerable time explaining to laptop buyers that the mobile GPUs are actually performing (at least) one rank lower than the desktop parts.

Overall I see ignorance of how much laptops are compromised left and right.