---
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen2.5-0.5B
pipeline_tag: text-generation
library_name: transformers
tags:
- qwen
- qwen2.5
- mistral
- mistral-small
- mistral-small-3.1
---

# Qwenstral-Small-3.1-0.5B

[Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B), but with the vocab of [mistralai/Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503) / [mistralai/Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501) transplanted using [transplant-vocab](https://github.com/jukofyork/transplant-vocab).

It can be used as draft model for Mistral-Small directly, but there is a more performant variant finetuned on Mistral's outputs:
- [alamios/Mistral-Small-3.1-DRAFT-0.5B](https://huggingface.co/alamios/Mistral-Small-3.1-DRAFT-0.5B)
- [alamios/Mistral-Small-3.1-DRAFT-0.5B-GGUF](https://huggingface.co/alamios/Mistral-Small-3.1-DRAFT-0.5B-GGUF)