# Rotational Quantization moderate compression

**URL:** <https://forum.weaviate.io/t/rotational-quantization-moderate-compression/22292>\
**Category:** General\
**Created:** [March 26, 2026, 9:37am UTC](https://forum.weaviate.io/t/rotational-quantization-moderate-compression/22292 "2026-03-26T09:37:24Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![Maxence\_Oden](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/maxence_oden/32/1495_2.png) [@Maxence\_Oden](https://forum.weaviate.io/u/Maxence_Oden)\
**Post date:** [March 26, 2026, 9:37am UTC](https://forum.weaviate.io/t/rotational-quantization-moderate-compression/22292/1 "2026-03-26T09:37:24Z")

</div>

Hello,

I recently read the excellent blog post on [8-bit Rotational Quantization](https://weaviate.io/blog/8-bit-rotational-quantization), which showcases its effectiveness. In the article, there is a table demonstrating the key metrics across low, moderate, and high compression levels.

However, I noticed in the [documentation](https://docs.weaviate.io/weaviate/configuration/compression/rq-compression#rq-parameters) that the 4-bit “moderate compression” does not currently seem to be available in Weaviate. Only the Low 8-bit and High 1-bit are implemented. I would love to be able to use it in my setup as it looks like a great sweet spot between space usage and recall.

Is the implementation of moderate compression on the roadmap, or are there current technical limitations preventing it ?

Thanks in advance for your time and insights!

---

<div class="post-metadata">

**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\
**Post date:** [March 27, 2026, 7:26pm UTC](https://forum.weaviate.io/t/rotational-quantization-moderate-compression/22292/2 "2026-03-27T19:26:00Z")

</div>

Hi @Maxence_Oden !!

Welcome back!

I will raise this with our research team, and circle back here.

Thanks for using Weaviate and pushing it 😉

Happy coding!

---

<div class="post-metadata">

**Author:** ![fraulty](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/fraulty/32/7909_2.png) [@fraulty](https://forum.weaviate.io/u/fraulty)\
**Post date:** [April 6, 2026, 2:28pm UTC](https://forum.weaviate.io/t/rotational-quantization-moderate-compression/22292/3 "2026-04-06T14:28:00Z")

</div>

I am just learning about this type of Quantization - looks super cool - maybe this might be interesting too (by Google Research):  
[TurboQuant: Redefining AI efficiency with extreme compression](https://research.google/blog/turboquant-redefining-ai-efficiency-with-extreme-compression/?utm_source=twitter&utm_medium=social&utm_campaign=social_post&utm_content=gr-acct)

Just gonna plug why I’m into quantization - I’m working on a way to democratize huge OSS LLMs for us GPUPoor folk haha - [4Bit-Forge (Compression: Quantization and Sparsity + CUDA Hella)](https://github.com/Pranshu-Bahadur/4Bit-Forge/tree/aimo3-minimax-m2.5)

---

<div class="post-metadata">

**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\
**Post date:** [April 6, 2026, 5:57pm UTC](https://forum.weaviate.io/t/rotational-quantization-moderate-compression/22292/4 "2026-04-06T17:57:37Z")

</div>

hi @fraulty !!

Welcome to our community 🤗

Our team was just discussing about it internally 😉

---

<div class="post-metadata">

**Author:** ![fraulty](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/fraulty/32/7909_2.png) [@fraulty](https://forum.weaviate.io/u/fraulty)\
**Post date:** [April 6, 2026, 6:27pm UTC](https://forum.weaviate.io/t/rotational-quantization-moderate-compression/22292/5 "2026-04-06T18:27:11Z")

</div>

@DudaNogueira oh that’s super cool to know! Thank you 😊- hope to learn a lot more from the community!