# Embedding models for retrieval | SAVRN Model Hub
Source: https://savrn.com/collections/embedding-models-for-retrieval
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Entries in this collection

Model · Sentence similarity

### [all-MiniLM-L6-v2](https://savrn.com/models/all-minilm-l6-v2)

Published by [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers)

Why it is here: The small baseline most retrieval stacks start with.

Open weights apache-2.0 23M parameters

[View model](https://savrn.com/models/all-minilm-l6-v2)

Model · Sentence similarity

### [bge-m3](https://savrn.com/models/bge-m3)

Published by [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai)

Why it is here: Multilingual, long-sequence retrieval.

Open weights mit

[View model](https://savrn.com/models/bge-m3)

Model · Feature extraction

### [multilingual-e5-large](https://savrn.com/models/multilingual-e5-large)

Published by [Liang Wang](https://savrn.com/model-publishers/intfloat)

Why it is here: A widely used multilingual encoder.

Open weights mit 560M parameters

[View model](https://savrn.com/models/multilingual-e5-large)

Model · Sentence similarity

### [all-mpnet-base-v2](https://savrn.com/models/all-mpnet-base-v2)

Published by [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers)

Why it is here: A stronger English baseline than MiniLM.

Open weights apache-2.0 109M parameters

[View model](https://savrn.com/models/all-mpnet-base-v2)

[Compare the first 4 models in this collection](https://savrn.com/models/compare?ids=all-minilm-l6-v2,bge-m3,multilingual-e5-large,all-mpnet-base-v2)

## Explore More

[Every collection](https://savrn.com/collections) · [The model directory](https://savrn.com/models) · [How a collection is decided](https://savrn.com/model-hub/methodology)