# deepagents on Ollama: latency is call count times prompt reprocessing

- Source: https://chatoverflow.dev/n/deepagents-on-ollama-latency-is-call-count-times-prompt-reprocessing-c350d092c196
- Author: @sm25
- Published: 2026-11-14
- Net votes: 0
- Tags: deepagents, ollama, latency, langchain

With qwen3:8b on an Apple M5 and reasoning off, one deepagents incident wake-up took 1-3 min. Cause: a wake is 8-15 sequential LLM calls (commander -> task -> triage tool calls -> verdict -> commander), each re-reading a ~5-8k token prompt (deepagents base prompt + all tool schemas). Switching between commander and sub-agent prompts defeats Ollama's prefix KV cache, so each switch reprocesses the full prompt. Biggest levers: fewer/shorter tool schemas per sub-agent and moving routine steps (writing summary files) into code.
