Nvidia may already be working on a future generation of AI-focused GPUs, codenamed Rubin
Despite very little information about Nvidia’s upcoming next generation Blackwell GPUAccording to a new report, plans already appear to be in place for the next generation.
The information comes from an analyst at TF Securities Ming Chi Kuo(reported by TechPowerUp). These new R100 chips have been codenamed Rubin (named after astronomer Vera Rubin). They are mainly focused on reducing power consumption, because high-end Blackwell GPUs are already reaching the highest kilowatt range and cannot continue to increase.
The other biggest takeaway is that Rubin will power future AI-based GPUs built with the TSMC-N3 node and using HBM4 stacked memory. These specifications are key to reducing energy consumption, which is critical considering Nividia is investing more in the AI market, which is notorious for its high energy costs. It’s great news for general users as it means the GPU will siphon less power and hopefully give you a discount on your electricity bill.
However, gamers will be sorely disappointed as, according to the report, Rubin is not made for gaming, but is completely dedicated to AI. What supports this is the mentioned 4x reticle design and Chip-On-Wafer-On-Substrate-L (CoWoS-L) technology in Ming-Chi Kuo’s post. Most likely, we could be looking at a large and expensive chip that could easily cost $50,000. This wouldn’t be the first time Such a huge price tag has been put on a chip.
So far we only have a mass production window of Q4 2025, which means consumers won’t get their hands on it until 2026.
Who is Rubin intended for?
As previously mentioned, the leaks reveal that the Rubin GPU is not made for gamers, but for specific AI uses. And judging by the number of chiplets and the final size of the GPU, we are looking at chips made for the professional market.
Most likely, data centers would be one of the main targets as they struggle to sustain themselves using current GPUs, and it will only get worse as power consumption increases for generations to come.
That leaves the important question of who else Rubin is for. Will Nvidia keep these chips exclusively in the enterprise space or will there be consumer versions for gaming and other general uses? It could also mean that Nvidia will alternate between consumer and business GPUs from now on, which makes sense considering how much profit the tech giant makes from the latter.