Groq to adopt NVIDIA Groq 3 LPX for inference cloud

Groq has announced it will be among the first adopters of NVIDIA Groq 3 LPX and will deploy it, alongside Vera Rubin NVL72, to its purpose-built AI inference cloud.

• Groq said it is working with Dell Technologies to deploy NVIDIA Groq 3 LPX and bring Vera Rubin NVL72 online at scale for its global AI inference cloud.
• The company said the platform will extend inference performance, with benchmarking claims including 3,400 output tokens per second on Gemma 4 31B with 100K token context; the release also says Groq became an NVIDIA Cloud Partner in August.
• Groq said its cloud serves more than six million developers, Fortune 500 enterprises, and thousands of AI-native companies, generating trillions of tokens every week across data centers in North America, Europe, the Middle East, and APAC.