NVIDIA Groq 3 LPX Enters Full Production, Nebius First to Adopt
NVDA sits 28% above its 52-week low of $164.07 on light trading volume (0.3× avg).
Summary
NVIDIA announced that Groq 3 LPX, its interactive AI inference accelerator, is now in full production. The product extends the Vera Rubin platform and delivers a record 3,400 output tokens per second in Artificial Analysis benchmarking, a 4x improvement over the nearest alternative. Nebius is the first AI cloud to adopt Groq 3 LPX, with plans to integrate it into its Token Factory inference platform. This follows NVIDIA's earlier Vera Rubin full-production announcement in June and reinforces its leadership in agentic AI infrastructure. The announcement highlights strong demand for high-speed inference, a key growth area for NVIDIA's data center business.
At the time of this announcement, NVDA was trading at $209.19 on NASDAQ in the Technology sector, with a market capitalization of approximately $5.1T. The 52-week trading range was $164.07 to $236.54. This news item was assessed with positive market sentiment and an importance score of 7 out of 10. Source: GlobeNewswire.