News Nvidia's Next-Gen GPUs are rumored to be codenamed 'Rubin,' arrive in 2025

[Admin]

Nvidia is working on R100 and GR200 GPUs that are due in 2025.

Nvidia's Next-Gen GPUs are rumored to be codenamed 'Rubin,' arrive in 2025 : Read more

 

[phatboe]

Alan Turing was not a physicist either.

 

[TJ Hooker]

It is noteworthy that Vera Rubin will be the first of Nvidia's architectures named after an astronomer.
[...]
Previously Nvidia named its GPU architectures only after physicists, including Fahrenheit, Celsius, Kelvin, Rankine, Curie, Tesla, Fermi, Kepler, Maxwell, Pascal, Volta, Turing, Ampere, Ada Lovelace, Hopper, and Blackwell.

Celsius and Keplar were also astronomers (although, in general, the distinction between astronomer and physicist can be a bit blurry). And several others weren't physicists (or weren't primarily physicists), e.g. 4 of the last 5.

 

[valthuer]

@JarredWaltonGPU Sorry to bother you about this, but, in light of these news, when exactly will the RTX-50 series be released?

Does the initial Nvidia roadmap, as revealed here

Nvidia Ada Lovelace Successor GPUs Slated for 2025 Release

With slow consumer GPU sales and massive interest in AI silicon, don't expect new Nvidia gaming GPUs anytime soon.

www.tomshardware.com

hold true to this day?

Is Blackwell still slated for a 2025 release?

I'm a little confused.

Thank you in advance for your time.

 

[JarredWaltonGPU]

@JarredWaltonGPU Sorry to bother you about this, but, in light of these news, when exactly will the RTX-50 series be released?

Does the initial Nvidia roadmap, as revealed here

Nvidia Ada Lovelace Successor GPUs Slated for 2025 Release

With slow consumer GPU sales and massive interest in AI silicon, don't expect new Nvidia gaming GPUs anytime soon.

www.tomshardware.com

hold true to this day?

Is Blackwell still slated for a 2025 release?

I'm a little confused.

Thank you in advance for your time.

I believe the original rumors were that consumer Blackwell would be out in 2024–2025, while data center Blackwell would be in 2024. Now, AFAIK, all indications are we won't see consumer Blackwell until 2025. Rubin at present looks more likely to be a 2025 data center only release.

The only people who know for certain are at Nvidia, and they're not going to say anything officially. I would be very surprised to see Blackwell consumer / RTX 50-series in 2024. It's possible, but I just don't expect it. Process node transitions are slowing down, data center and AI are picking, and so Nvidia has no real need to rush out a new consumer architecture.

If AMD were to launch a more competitive RDNA 4 next year, then I think Nvidia would move the launch window forward. There's also still the question of what process node consumer Blackwell will use. TSMC N3 / 3N would seem likely, but at the same time, that might be too expensive and we could get 4N again. I'm probably 80–90 percent convinced it will be a "3nm-class" node, but "refined 4N" isn't totally impossible.

 

[Googulator]

"GR200" sounds like a Grace-Rubin combo chip. (Expect the first letter to change, as in "VR200", if they choose to release a new CPU core "Vera" too.)

 

[valthuer]

I believe the original rumors were that consumer Blackwell would be out in 2024–2025, while data center Blackwell would be in 2024. Now, AFAIK, all indications are we won't see consumer Blackwell until 2025. Rubin at present looks more likely to be a 2025 data center only release.

The only people who know for certain are at Nvidia, and they're not going to say anything officially. I would be very surprised to see Blackwell consumer / RTX 50-series in 2024. It's possible, but I just don't expect it. Process node transitions are slowing down, data center and AI are picking, and so Nvidia has no real need to rush out a new consumer architecture.

If AMD were to launch a more competitive RDNA 4 next year, then I think Nvidia would move the launch window forward. There's also still the question of what process node consumer Blackwell will use. TSMC N3 / 3N would seem likely, but at the same time, that might be too expensive and we could get 4N again. I'm probably 80–90 percent convinces it will be a "3nm-class" node, but "refined 4N" isn't totally impossible.

Yeah, i too would be surprised to see the RTX 50 series out in 2024, considering what beast of a card 4090 is.

Nvidia, have no competition, so there's no need to rush things.

Thank you for taking the time to reply.