Despite the top-tier graphics cards from the past few generations being absolute power hogs, drawing hundreds upon hundreds of watts to deliver what feels like increasingly-modest performance gains, their laptop counterparts have taken enormous leaps in capabilities. AMD, Nvidia, and Intel have made great strides in what onboard graphics and dedicated graphics chips can do with relatively limited power and cooling options.
But even so, mobile GPU naming feels like a scam. The latest example is the flagship Nvidia RTX 50 GPU of this generation, the RTX 5090. On desktop it’s about 30% faster than an RTX 4090, but with boatloads more memory, support for the latest multi frame generation technology, and a near-600W TDP to go with it.
In comparison, the RTX 5090 mobile pulls just 160W at full tilt, so obviously its performance is noticeably worse. Indeed, it’s around half that of the desktop 5090. But while that’s a truly impressive feat, it showcases how out of whack the naming scheme is. The RTX 5090 mobile isn’t like an RTX 5090, it’s more like a 4070 Ti Super.
“Obviously” worse
I hate the word obviously, and “of course,” is a close second. I do my best not to use them when writing anything because if it truly is obvious, you don’t need to say it, and if you do, you’re just going to make some people feel inadequate or inferior.
So I think it’s noteworthy that my first instinct was to write in the above section that “obviously its performance is noticeably worse.” Because if you’ve been in this space long enough, of course the 5090 mobile is worse. It has a much lower TGP and it’s in a laptop. The cooling is obviously going to be inferior to a full graphics card and overall performance simply cannot match the desktop version.
But what is obvious to you or I, is unlikely to be for everyone. For people out there who don’t live and breathe Nvidia and AMD rivalries, and just read a few headlines about what the “best,” is, someone could easily buy an RTX 5090 laptop thinking they were getting 5090-like performance, only to be disappointed when that is far from the case. Indeed, even those who try to find out more might trip themselves up looking up information on the “5090,” only to find that the 5090 they bought is nothing like the one all reviewers are hailing as the fastest GPU ever.
The same goes for a range of other GPUs, too, as they’re never as good as their desktop counterparts. There are also massive differences between different mobile GPUs and their performance, simply because the laptop’s size, power profile, or cooling design are different.
Laptop graphics are confusing enough, without the GPUs being named after something they have no real comparison to. Not on performance, not on power, not on capability. All it says to buyers is that this is the top option, and even then that’s not guaranteed laptop to laptop.
Fair names
AMD’s method of naming mobile graphics is a little better, slapping “M” on the end of its mainstream mobile graphics options. That at least differentiates the mobile options from the desktop and gives potential buyers a unique phrase to Google in their search for clarification. Though it still suggests there’s a direct correlation between them and their desktop counterparts. Apple and Qualcomm do it by graphics cores, but that’s even more opaque than Nvidia’s solution.
What I’d love to see is something related to its power limit. I’m not a marketing guy, so I’m not going to pretend I know a good way to spin this so it helps sell, but how about a 59-160 for those top laptops? 50 series, 9-class, 160W. Then laptop manufacturers could modify the name of the GPU they’re using based on the wattage available to it.
It wouldn’t be perfect, but it would give consumers a direct name to Google for third-party testing and comparisons, and a clearer understanding of what it was they were buying, and what they can expect for it. It would even let you have fun names for the desktop. Tell me Jensen Huang wouldn’t love to say you can buy the 59-575 for 2995?
Helping the customer be right
At the end of the day, most laptop buyers don’t have the time or interest to spend hours getting to grips with what laptop components are and their specific, generationally-unique naming schemes, and how mobile options with the exact same name might differ. An RTX 5090, or any other mobile GPU, is going to appear like the desktop variant to the uninitiated, as most are, giving a false impression of what’s possible and overly-justifying the sky-high prices of high-end gaming laptops.
Better naming wouldn’t just help those who have no idea what they’re looking at, though; It would even help those of us who do. Just being able to Google the specific GPU that a laptop uses for comparisons, rather than having to cross reference it with ones that have a certain power ceiling or memory configuration, would be a huge time saver. It would help the laptops that truly push the envelope to stand out, too.
I’m not asking for miracles, just if a laptop performs like an RTX 4070 Ti Super, don’t call it an RTX 5090. This isn’t just about ending something that feels deliberately misleading, it’s about helping consumers make more informed purchasing decisions, which in 2025 should be the norm, not the exception.
