# Discourse AI with local ollama Internal Server Error

**URL:** https://meta.discourse.org/t/discourse-ai-with-local-ollama-internal-server-error/392251
**Category:** Bug
**Tags:** ai
**Created:** [December 27, 2025, 9:20pm UTC](https://meta.discourse.org/t/discourse-ai-with-local-ollama-internal-server-error/392251 "2025-12-27T21:20:05Z")
**Posts on this page:** 1
**Showing post:** 2

<div class="post-metadata">

### Author: ![luftaquila](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/luftaquila/32/434823_2.png) [@luftaquila](https://meta.discourse.org/u/luftaquila)
#### Post date: [December 27, 2025, 9:46pm UTC](https://meta.discourse.org/t/discourse-ai-with-local-ollama-internal-server-error/392251/2 "2025-12-27T21:46:30Z")

</div>

I’ve found out that the model was the problem. Using `qwen2.5:3b` with Groq as provider and QwenTokenizer makes the test success.

---

_[View the full topic](https://meta.discourse.org/t/discourse-ai-with-local-ollama-internal-server-error/392251)._