Don't use all-MiniLM-L6-v2 for new vector embeddings datasets.

Yes, it's the open-weights embedding model used in all the tutorials and it was the most pragmatic model to use in sentence-transformers when vector stores were in their infancy, but it's old and does not implement the newest advances in architectures and data training pipelines, and it has a low context length of 512 when embedding models can do 2k+ with even more efficient tokenizers.

For open-weights, I would recommend EmbeddingGemma (https://huggingface.co/google/embeddinggemma-300m) instead which has incredible benchmarks and a 2k context window: although it's larger/slower to encode, the payoff is worth it. For a compromise, bge-base-en-v1.5 (https://huggingface.co/BAAI/bge-base-en-v1.5) or nomic-embed-text-v1.5 (https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) are also good.

▲

xfalcox 3 hours ago | parent | next [-]

I am partial to https://huggingface.co/Qwen/Qwen3-Embedding-0.6B nowadays.

Open weights, multilingual, 32k context.

▲

SteveJS 2 hours ago | parent | next [-]

Also matryoshka and the ability to guide matches by using prefix instructions on the query.

I have ~50 million sentences from english project gutenberg novels embedded with this.

	▲	dleeftink an hour ago \| parent \| next [-]
		Why would you do that and I'd love to know more
	▲	Tostino an hour ago \| parent \| prev [-]
		What are you using those embeddings for, If you don't mind me asking? I'd love to know more about the workflow and what the prefix instructions are like.

▲

greenavocado 28 minutes ago | parent | prev [-]

It's junk compared to BGE M3 on my retrieval tasks

▲

kaycebasques 2 hours ago | parent | prev | next [-]

One thing that's still compelling about all-Mini is that it's feasible to use it client-side. IIRC it's a 70MB download, versus 300MB for EmbeddingGemma (or perhaps it was 700MB?)

Are there any solid models that can be downloaded client-side in less than 100MB?

	▲	nijaru 11 minutes ago \| parent \| next [-]
		For something under 100 MB, this is probably the strongest option right now. https://huggingface.co/MongoDB/mdbr-leaf-ir
	▲	intalentive 20 minutes ago \| parent \| prev [-]
		This is the smallest model in the top 100 of HF's MTEB Leaderboard: https://huggingface.co/Mihaiii/Ivysaur Never used it, can't vouch for it. But it's under 100 MB. The model it's based on, gte-tiny, is only 46 MB.

▲

SamInTheShell 29 minutes ago | parent | prev | next [-]

I tried out EmbeddingGemma a few weeks back in AB testing against nomic-embed-text-v1. I got way better results out of the nomic model. Runs fine on CPU as well.

▲

dangoodmanUT 3 hours ago | parent | prev [-]

yeah this, there's much better open weights models out there...