# Time out when running Ollama model

**URL:** <https://community.crewai.com/t/time-out-when-running-ollama-model/5722>\
**Category:** CrewAI Community Support\
**Created:** [May 9, 2025, 7:03am UTC](https://community.crewai.com/t/time-out-when-running-ollama-model/5722 "2025-05-09T07:03:53Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Joe\_Woo](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/joe_woo/32/3615_2.png) [@Joe\_Woo](https://community.crewai.com/u/Joe_Woo)\
**Post date:** [May 9, 2025, 7:03am UTC](https://community.crewai.com/t/time-out-when-running-ollama-model/5722/1 "2025-05-09T07:03:53Z")

</div>

I am getting this litellm.exceptions.APIConnectionError: litellm.APIConnectionError: OllamaException - litellm.Timeout: Connection timed out after 600.0 seconds. And how do I resolve it. It does not look like the solution provided by cursor works at all.

---

<div class="post-metadata">

**Author:** ![zinyando](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/zinyando/32/4435_2.png) [@zinyando](https://community.crewai.com/u/zinyando)\
**Post date:** [May 9, 2025, 10:58am UTC](https://community.crewai.com/t/time-out-when-running-ollama-model/5722/2 "2025-05-09T10:58:08Z")

</div>

Is the model you want to use loaded? It seems like you might be getting that error because litellm can’t establish a connection with the ollama model.

Just a guess here. Try `ollama run your_model` first and make sure it’s working. Then try running your agent again.

---

<div class="post-metadata">

**Author:** ![jklre](https://avatars.discourse-cdn.com/v4/letter/j/b4bc9f/32.png) [@jklre](https://community.crewai.com/u/jklre)\
**Post date:** [May 9, 2025, 10:35pm UTC](https://community.crewai.com/t/time-out-when-running-ollama-model/5722/3 "2025-05-09T22:35:33Z")

</div>

How complex is your project and what are you trying to do? Aslo what crew AI features do you need. Litellm was introduced in 0.6x of crew. So if you dont need all the new bells and whistles mayby downgrade? Also like the other comment I would look at making sure your endpoint is in good status and has the model avaliable.
