The latest performance rumor surrounding AMD’s RDNA 4 GPUs may have you worried, but we don’t think there’s any reason to panic
AMD’s next generation of graphics cards, which will logically be sold as RX 8000 models, could be mostly about correcting problems with existing RDNA 3 GPUs, and not that big of a step up in performance.
This idea comes from a leaker we haven’t heard from in a while, Wjm47196, which has resurfaced in the Chiphel forums (via Wccftech) with chatter surrounding the next generation of RDNA 4 GPUs (and RDNA 5 to boot).
In view of possible translation issues from Chinese, and the fact that this is just a rumor, we are told that RDNA 4 is just a “bug fix” and that these graphics cards are “similar to RDNA 3.”
This means that with the next generation of RDNA 4, AMD is mainly addressing the issues surrounding RDNA 3 performance – which are well documented in terms of speculation anyway – rather than moving forward with an entirely new approach for its Radeon graphics cards.
The new architecture and “clean sheet design” as the leaker puts it, is happening with RDNA 5, and this may even involve some sort of name change, we’re told, although Wjm47196 admits they’re not sure about that.
As for RDNA 4 performance, the leaker believes that the best next-generation AMD graphics card should be comparable to the RX 7900 XT.
That mirrors what we’ve heard before – although we might expect something punchier than the 7900 XT (well, fingers crossed). This of course underlines the long-standing rumor that RDNA 4 will top out in the mid-range segment, with flagship performance at that level.
While that means overall performance won’t be better than AMD’s current generation of GPUs – in fact, it will likely be a bit worse and lag behind the 7900 XTX – what will improve is ray tracing performance.
Analysis: The potential good news about the potential bad news
It’s true that the talk about RDNA 4 graphics cards is mostly about ironing out the issues with RDNA 3 rather lowering expectations for these next-gen products, as does the proposed level of performance here. In fact, though, things are only being toned down a little bit from what has already come out of the rumor mill.
We know they won’t be a huge step forward, and we know the RX 8000 will top out in the mid-range in terms of performance, near the RX 7900 XT (assuming all the rumors out there somehow way not very wrong – unlikely).
Yes, the claim that RDNA 4 would just be a ‘bug fix’ may seem concerning in terms of a lack of progress, but in some ways it may not be a bad thing. Especially since AMD will have to make these next-gen mid-range GPUs attractive, and it seems like the strategy to do that will be to make sure they’re more stable and reliable (which is good, of course) and boost ray tracing .
That is not enough? Well, this is why even that can be seen as a positive, because AMD will then have to generate interest in these GPUs in some other way, and the obvious route to do that is through pricing.
If Nvidia has Blackwell’s big guns (perhaps the RTX 5090 and 5080 later this year), then AMD will have to wave the white flag as far as the battle for GPU powerhouses is concerned, but still be able to attack on the value proposition front . Correction: it must attack on the value front so that the next-gen Radeon lineup makes sense and gets these cards on our list of the best GPUs.
And in some ways that could be the best news ever: mid-range GPUs that actually look affordable, and let’s face it, they still aren’t with the current generation of graphics cards (even though we’re seeing a number of significant price reductions). territory of late). We’ve been treated to other speculation in the past suggesting this could be the case.
RDNA 5 will be the one to watch though, and this is also a persistent theme from the rumor mill. AMD is planning a big leap with this next generation of GPUs, and if the name change theory proposed here is correct, that underlines potential plans to revolutionize Radeon GPUs (to the point where they might not even be Radeon anymore?) .