# Random discussion about Discourse LLM setup

**URL:** https://meta.discourse.org/t/random-discussion-about-discourse-llm-setup/410507
**Category:** Support
**Created:** [October 1, 2024, 5:40am UTC](https://meta.discourse.org/t/random-discussion-about-discourse-llm-setup/410507 "2024-10-01T05:40:38Z")
**Posts on this page:** 1
**Showing post:** 12

<div class="post-metadata">

### Author: ![jrgong](https://avatars.discourse-cdn.com/v4/letter/j/c57346/32.png) [@jrgong](https://meta.discourse.org/u/jrgong)
#### Post date: [April 11, 2025, 11:20am UTC](https://meta.discourse.org/t/random-discussion-about-discourse-llm-setup/410507/12 "2025-04-11T11:20:22Z")

</div>

> [@Discourse AI - Large Language Model (LLM) settings page](https://meta.discourse.org/t/discourse-ai-large-language-model-llm-settings-page/319903/1):
>
> - Gemini Flash 2.0

This model is not listed on 3.4.2 - are those pre-configs only available on 3.5 and I have to add them manually?

Edit: Also what option do I choose for “Tokenizer” when using Grok 3 models?

 ![Screenshot 2025-04-11 at 13.50.14](https://global.discourse-cdn.com/meta/original/4X/4/7/f/47f10492d01744131bc9488d761bb286532030dc.png)

---

_[View the full topic](https://meta.discourse.org/t/random-discussion-about-discourse-llm-setup/410507)._