Embedding GGUF models
2342 GGUF models: embedding models for search and RAG. Sizes run from 1M to 671B parameters. The longest trained context is 1024K tokens.
About Embedding GGUF models
2,342 GGUF models are filed under Embedding: embedding models for search and RAG. The most downloaded are mxbai-embed-large-v1, nomic-embed-text-v1.5 and Embeddinggemma 300m. Parameter counts run from 1M to 671B, and the longest trained context window is 1024K tokens.
Embedding models turn text into vectors for search and retrieval. They are small, and you use them through an embeddings endpoint instead of a chat prompt. The families you will see most are Qwen (519), BGE (291) and Jina (102).
Frequently asked questions
What are Embedding GGUF models?
Embedding models for search and RAG. There are 2,342 of them on this site.
Which Embedding GGUF model should I start with?
The most downloaded is mxbai-embed-large-v1. Choose the size that fits your GPU, then a Q4_K_M quant unless you have memory to spare.