> ## Documentation Index
> Fetch the complete documentation index at: https://elatoai.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Qwen3

> Use Qwen3 from mlx-community as a multilingual local LLM for your ESP32 AI toy.

Qwen3, Qwen3.5 and Qwen3.8 models (0.6B up to 27B in the README) from [`mlx-community`](https://huggingface.co/mlx-community) work with OpenToys and are a good fit if your toy speaks Chinese or another non-English language. Paste the repo name into the **Models** page to switch.

> [!NOTE]
>
> Qwen3 can produce reasoning text before its answer. OpenToys strips it before the reply goes to text-to-speech.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.