OpenAI Is Set to Be the Biggest Customer for the Upcoming NVIDIA-Groq AI Chip, Allocating 3GW of Dedicated ‘Inference Capacity’
OpenAI’s newest partnership with NVIDIA not only focuses on Vera Rubin but also on inference capacity, which will be provided by the upcoming NVIDIA-Groq solution.
OpenAI Now Pivots Towards NVIDIA For Inference, Likely Being Optimistic With the Upcoming Groq Solution
OpenAI is currently engaged in financing deals with infrastructure partners all across the AI industry, and the AI giant recently announced $110 billion in fresh capital, driven by the likes of NVIDIA, SoftBank, and Amazon. OpenAI calls the investments a necessity to keep the AI bandwagon up and running, and they have been one of the ways the firm has secured the computing power it needs. A WSJ report reveals that NVIDIA will showcase its Groq-focused “processor” at this year’s GTC 2026, in line with our previous reporting.
More specifically, OpenAI will be the biggest customer of the upcoming solution, which is an interesting decision. In the recent commitment by NVIDIA into OpenAI, it was revealed that the latter will use 3GW of “dedicated inference capacity”, likely coming from what NVIDIA will showcase in March. Earlier reports have suggested that inference is a major concern for OpenAI in recent times, and that the company had been ‘displeased’ with what NVIDIA had been offering to address inference.
OpenAI has agreed to become one of the largest customers of the new processor, some of the people said, representing a major win for Nvidia. The ChatGPT maker, which is one of Nvidia’s largest customers, has spent the past few months shopping for more efficient alternatives to Nvidia’s chips.
– WSJ
OpenAI was reported to be in talks with Cerebras and Groq as well to enter into agreements focused on providing optimal performance for latency-sensitive workloads. But now, it appears that OpenAI is sticking with NVIDIA, likely indicating that the upcoming solution built around Groq’s LPUs is promising enough for the AI giant to commit to 3GW of capacity. Regarding what we expect from the NVIDIA-Groq arrangement, the most likely solution is a hybrid compute tray configuration, as discussed here.
Image Credits: NVIDIA
For now, we expect major announcements from NVIDIA at this year’s GTC, focusing on Vera Rubin, possibly next-gen Feynman, and the solution built around Groq.
Follow Wccftech on Google to get more of our news coverage in your feeds.
