Mercury 2.5 LLM hits 770 tokens per second
- LLM: 28 events in the last 90 days
- Previous: 1 days earlier · Turn text input into actions with Needle, a 14MB function-calling LLM
What happened
Analysis of Inception's Mercury 2.5 and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.
Summary assembled by rule from the sources below
Why it's spreading
Sources
Community
- Mercury 2.5 LLM hits 770 tokens per secondHacker News