Nvidia Groq 3 LPX Inference Rack Hits Full Production, Nebius Signs as First Cloud Customer

Nvidia said its Groq 3 LPX, the dedicated inference accelerator built from its $20B Groq acqui-hire, has entered full production and slots into the Vera Rubin platform with up to 256 LPX accelerators per rack. Nebius will be the first cloud customer, deploying LPX racks alongside Vera CPUs and Rubin GPUs in its Token Factory. A benchmark from Artificial Analysis clocks 3,400 output tokens per second on Gemma 4 31B at 100K context, and SpaceX said its next-generation AI stack — including orbital data centers — will run on Nvidia's Vera CPUs.