# Choosing between monolingual and multilingual models

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchoosing-between-monolingual-and-multilingual-models%2F88038%3E%5C
**Category:** Models\
**Created:** [May 23, 2024, 9:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchoosing-between-monolingual-and-multilingual-models%2F88038 "2024-05-23T09:49:49Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![fairp](https://avatars.discourse-cdn.com/v4/letter/f/2acd7d/32.png) [@fairp](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ffairp)%5C
**Post date:** [May 23, 2024, 9:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchoosing-between-monolingual-and-multilingual-models%2F88038%2F1 "2024-05-23T09:49:49Z")

</div>

Hello to the community. I have a question. I want to choose a sentence transformer model that would be used to create word embeddings.  
Those embeddings would then be used for semantic search. My problem is that i want to use a model for the German language and i am not sure if it is better to use a multilingual model or a monolingual model that was only trained using German examples.  
What is the best way to compare thier performances and see which model to use? Is there a good idea to perform clustering or classification using some of them and evaluate thier results?