A new class of AI inference is arriving:
@GroqInc is among the first to bring
@nvidia Groq 3 LPX and Vera Rubin NVL72 to market - and it's deployed with Dell Technologies.
✨The benchmark: 3,400 output tokens/sec, 4x higher interactivity than the nearest alternative. More than six million developers and thousands of enterprises are already building on GroqCloud. This is where they go next.