This Year’s GTC, Likely Pointing Toward Rubin or Next-Gen Feynman AI Lineups

NVIDIA’s CEO has spoken about what we could see next at the company’s GTC 2026 event, hinting that we could see chips that the “world has never seen before”.

NVIDIA’s Next Stage at GTC Could Feature Next-Gen Feynman Chips, Possibly Showcasing Groq’s LPU Integration

NVIDIA has been at the forefront of the AI technological revolution, mainly through its compute portfolio and its ability to keep up with its product cycles. At CES 2026, we saw Team Green showcase its Vera Rubin AI lineup, revealing it was in full production and included six newly designed chips, including the Vera CPUs and Rubin GPUs. And now, while speaking with Korean media, NVIDIA’s CEO Jensen Huang says this year’s GTC will see the unveiling of products the world has never seen before.

We’ve prepared several new chips the world has never seen before. Nothing is easy because all technologies are at their limits.

– NVIDIA’s CEO

Well, this is undoubtedly an optimistic statement coming from Jensen, and considering his track record, NVIDIA’s CEO has delivered upon his promises. The report doesn’t specifically mention what chip Jensen talks about, but considering that it is something “never seen before”, our best guess would likely be either a derivative chip coming from the Rubin lineup, such as Rubin CPX we saw earlier, or NVIDIA could throw a surprise and decide to unveil their next-gen Feynman chips, which are known to be ‘revolutionary’ as well, but that remains to be seen.

NVIDIA currently competes in a market where compute demand changes from quarter to quarter. For example, with Hopper and Blackwell, pre-training was the primary requirement; however, with Grace Blackwell Ultra and Vera Rubin, inference has taken over, where latency and memory bandwidth are the primary bottlenecks. And, with Feynman, we do know that NVIDIA is exploring a more extensive SRAM-focused integration, possibly integrating LPUs through 3D stacking, but this isn’t confirmed for now.

However, Jensen has committed to the fact that broader acquisitions and partnerships are what keep the company ahead in the AI race:

NVIDIA has great partners and amazing startups, and we are investing across the entire AI stack. AI is not just a model; it’s an entire industry encompassing energy, semiconductors, data centers, the cloud, and the applications built on top of it.

For those unaware, NVIDIA’s GTC keynote will commence on March 15th, back in San Jose, California, where the primary discussions will be on the next era of the AI infrastructure race.

https://wccftech.com/nvidia-ceo-to-unveil-chips-that-the-world-has-never-seen-before/amp/