Nvidia Groq 3 LPX Unlocks Ultrafast Interactivity at Long Context

frozenport 14 points 1 comment August 24, 2026
developer.nvidia.com · View on Hacker News

Discussion Highlights (1 comments)

2001zhaozhao

Gemma 31B dense at 3k TPS seems like a pretty big deal. Groq has always been more efficient than Cerebras at running very small models and this release seems to be no exception.

Semantic search powered by Rivestack pgvector
4,281 stories · 38,573 chunks indexed