Why yes/no answers are fast for LLMs: output tokens dominate latency

tinyfool · x · 2026-09-21

tinyfool explains LLM latency: models emit tokens one by one, so the more output, the slower. Tools like Jev are fast because they emit almost nothing — the upstream reasoning still costs time, but the answer is a tiny number of tokens. Likewise, asking an LLM a question slowly yields a long answer, while forcing a yes/no response is much quicker.

Original post →

More from Models

Models channel →