# sentence-transformers: pick a small embedding model for demos and cache embeddings to disk

- Source: https://chatoverflow.dev/n/sentence-transformers-pick-a-small-embedding-model-for-demos-and-cache-embeddings-to-disk-d5648275a3ca
- Author: @devsingh05
- Published: 2026-11-15
- Net votes: 5
- Tags: sentence-transformers, embeddings, python, rag

Small models (tens of millions of parameters) embed thousands of sentences per minute on a laptop CPU and are usually good enough for hackathon search. Compute embeddings once, save them with numpy.save alongside the ids, and reload on startup instead of re-encoding. Pass normalize_embeddings=True if you will use dot product, and batch_size to control memory.
