Nvidia RTX 5090: rumors, possible specs, and everything we know (2024)

Nvidia's RTX 5000-series graphics cards have been clinging to the tech world grapevine for well over a year now, with one of the most speculated cards being the Nvidia RTX 5090. It's the flagship of the line-up and will likely be the best graphics card on the market once it actually launches, certainly in terms of raw performance.

Given how well the current-gen flagship Nvidia RTX 4090 was reviewed (we cited it as one of the best graphics cards ever released), there are high expectations for next-gen cards, and the RTX 5090 in particular bears the brunt of that. The Nvidia Lovelace generation as a whole has been a mixed bag in terms of performance and pricing, which adds even more pressure to the 5090 to succeed in both aspects.

However, it's still too early to say whether it can live up to these expectations, with plenty more to learn about until it's officially revealed by Nvidia. For now, let's go over what we do know thanks to all the rumors and leaks, which have been plentiful.

Nvidia RTX 5090: Cut to the chase

• What is it?Nvidia's rumored flagship for its next generation of RTX graphics cards
• How much does it cost?Unknown at this time, but will likely be similar in cost to the RTX 4090 - if not a bit pricier
• When can I get it?The earliest we expect to see the Nvidia RTX 5090 would be late 2024 or early 2025, but the RTX 5080 might arrive first

Nvidia RTX 5090: Latest news

• Nvidia RTX 5080 and 5090 may not turn up this year after all – next-gen GPUs might be launched at CES 2025
• Nvidia RTX 5090 GPU could have less VRAM than previously rumored – but that might be good news for gamers
• If you’re not excited about Nvidia’s RTX 5090 yet, you will be after seeing Micron’s new VRAM that’s rumored for the GPU
• Nvidia RTX 5090 rumors continue to suggest this graphics card will not just be powerful, but also miraculously slim
• Nvidia RTX 5090 could pack 32GB of VRAM and be a slimmer graphics card than the RTX 4090

Nvidia RTX 5090: Release date

Though there's no official release date for the Nvidia RTX 5090, thanks to the tech rumor mill we do have an idea as to when the card could come out. And since the global chip shortage has eased up, there aren't any predicted delays for the next generation chip either.

All signs seem to point to late 2024 at the absolute earliest, or early 2025, which ties into the normal 18 to 24-month release cycle that Nvidia usually abides by with its GeForce graphics cards.

There are also recent rumors suggesting that it could be coming out after the RTX 5080, and that could push back the RTX 5090's release to 2025. The rumor mill seems to have been a bit back and forth on this of late, so we'll just have to keep a watchful eye on fresh chatter from the grapevine. But right now, speculation is still leaning towards the RTX 5080 hitting the shelves first, and a possible CES 2025 launch (perhaps both of these next-gen Blackwell graphics cards could be revealed at that event, even if the RTX 5080 goes on sale ahead of the flagship).

Nvidia RTX 5090: Specs

There has been quite a bit of info coming out concerning the Nvidia RTX 5090's specs, with the flagship graphics card being based on Nvidia's Blackwell architecture.

We've learned that the 16-pin 12V-2x6 power connector could be a standard for the 5090 and other 5000-series cards, meaning even third-party board partners would need to use it. The RTX 5090 is also rumored to feature a 448-bit memory bus, and 28Gbps GDDR7 memory modules which would be 33% faster than the 21Gbps memory modules in the RTX 4090. Another rumor speculates that the next-gen flagship card will sport 28GB of VRAM, too.

We recently heard rumors that Nvidia would finally be switching some of its Blackwell GPUs over to a multi-chiplet module (MCM) design, following in the footsteps of AMD and Intel. Whether this will include the Nvidia RTX 5090 isn't clear, however, since the rumors only specified the GB100 GPU, which is a commercial-grade chip for servers, data centers, and industrial use. If it did happen for the GeForce flagship - admittedly, it's not looking likely at this point, mind - it'd be a possibly major boost for the RTX 5090.

We've also seen some purported specs for an RTX 5090 from Chiphell forum user Panzerlied, a fairly reliable hardware leaker. According to a now-deleted post, the RTX 5090 will boast some impressive spec upgrades over the RTX 4090:

Also rumored is that Nvidia is set to ramp up the base clock speed of the RTX 5090 so it'll be something like 30% faster than the 4090.

If all these specs pan out, this should give the RTX 5090 a massive gen-on-gen boost, with the same post that detailed the specs claiming that the RTX 5090's performance should be 1.7 times faster than the RTX 4090, which is downright wild.

Other rumors have suggested more like a 1.5x or 1.6x boost, which would still be a huge upgrade - whatever the case, the rumor mill seems pretty convinced this will be a very beefy flagship GPU upgrade.

Another piece of speculation well worth noting is that despite this apparent cranking up of performance levels, there are theories floating around that Nvidia is somehow going to manage to make the RTX 5090 slimmer than the current-gen flagship. If that pans out, too, well, this GPU is really going to be something special.

Nvidia RTX 5090: What to expect

As mentioned, expectations are currently leaning towards the RTX 5090 arriving second, following hot on the heels of the RTX 5080, which might be the initial Blackwell GeForce graphics card - though we still don't know for sure by any means. With some rumors pointing to an early 2025 launch, at CES, as we already noted, we could even see both the RTX 5090 and 5080 get their initial reveal at the show in January 2025 (if not before).

Another point recently raised is that the RTX 5080 may have a decent volume of stock available at launch, so can we hope the same might be true of the RTX 5090? Well, probably not, as the trouble with the Blackwell flagship is that Nvidia is surely going to be prioritizing AI GPUs over it. Time will tell, and we certainly have to take all of this with a hefty grain of salt for the time being.