9 points | by frozenport 2 hours ago
1 comments
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.
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.