# Train 400x faster Static Embedding Models with Sentence Transformers

DevFeed: [Train 400x faster Static Embedding Models with Sentence Transformers](<https://devfeed.tech/articles/train-400x-faster-static-embedding-models-with-sentence-transformers-7491.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/static-embeddings>)

Author: Tom Aarsen

Published: 2025-01-15T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [sentence-transformers](<https://devfeed.tech/topics/sentence-transformers.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [On-device AI](<https://devfeed.tech/topics/on-device-ai.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [community](<https://devfeed.tech/tags/community.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [edge-computing](<https://devfeed.tech/tags/edge-computing.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [guide](<https://devfeed.tech/tags/guide.md>), [inference](<https://devfeed.tech/tags/inference.md>), [low-power](<https://devfeed.tech/tags/low-power.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [recommendation-systems](<https://devfeed.tech/tags/recommendation-systems.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [sentence-transformers](<https://devfeed.tech/tags/sentence-transformers.md>)

## AI overview

This Hugging Face blog post presents a method for training static embedding models that run 100x to 400x faster on CPU while retaining most of the quality of state-of-the-art models. It introduces released models for English retrieval and multilingual similarity, along with their training strategy, scripts, evaluation reports, and datasets. The approach supports on-device, in-browser, edge, low-power, and embedded use cases.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.