Other

NVIDIA says Groq 3 LPX, integrated with Vera Rubin NVL72, achieved 3,431 output tokens per second on a 100K-context Gemma 4 31B benchmark.

Verified Emerging 1 source
First seen
Last updated
Event ID
6c03f031-198e-4d7d-98fa-c8a4b3fda5da

Source trail

  1. developer.nvidia.comHow NVIDIA Groq 3 LPX Unlocks Ultrafast Interactivity at Long Context on NVIDIA Vera Rubin
    Announcement Published
    Open source ↗

Observation timeline

  1. Announcement Publisheddeveloper.nvidia.com · ORIGINAL

Research & reporting

Editorial work is a separate, human-published layer. It never defines this Event.

No editorial Article is attached. The Event remains public because editorial publication is optional.