# Self-Hosting Embeddings for DiscourseAI

**URL:** https://meta.discourse.org/t/self-hosting-embeddings-for-discourseai/290925
**Category:** Self-Hosting
**Tags:** ai, ai-search, related-topics
**Created:** [January 8, 2024, 8:49pm UTC](https://meta.discourse.org/t/self-hosting-embeddings-for-discourseai/290925 "2024-01-08T20:49:12Z")
**Posts on this page:** 1
**Showing post:** 9

<div class="post-metadata">

### Author: ![Isambard](https://avatars.discourse-cdn.com/v4/letter/i/858c86/32.png) [@Isambard](https://meta.discourse.org/u/Isambard)
#### Post date: [November 29, 2024, 1:06pm UTC](https://meta.discourse.org/t/self-hosting-embeddings-for-discourseai/290925/9 "2024-11-29T13:06:41Z")

</div>

To save space, is it possible to use quantized embeddings? I’d like to use binary quantized embeddings to really cut down the storage size. Having done some tests, I get \>90% performance with 32x less storage!

---

_[View the full topic](https://meta.discourse.org/t/self-hosting-embeddings-for-discourseai/290925)._