# Small miniLM model for multilingual

**URL:** <https://discuss.huggingface.co/t/small-minilm-model-for-multilingual/10583>\
**Category:** 🤗Transformers\
**Created:** [October 7, 2021, 9:12am UTC](https://discuss.huggingface.co/t/small-minilm-model-for-multilingual/10583 "2021-10-07T09:12:37Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![sachin](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/sachin/32/26534_2.png) [@sachin](https://discuss.huggingface.co/u/sachin)\
**Post date:** [October 7, 2021, 9:12am UTC](https://discuss.huggingface.co/t/small-minilm-model-for-multilingual/10583/1 "2021-10-07T09:12:37Z")

</div>

Hi!

Just wondering if there was a smaller model than ditilbert and that is mutilingual that I can use. Currently I am using a sentence transformer model (sentence-transformers/all-MiniLM-L12-v2) but I feel like this was optimized for something else, and results will be sub optimal if I use this for classification.

I know that there is [this](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) model by microsoft which looks promising but it’s only for English. It’s similarly [named multingual model](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) is unfortunately much larger at 450MB and is bigger than the multilingual distilbert model.