Hey HN, which embedding models are people using? There has been so much development around foundational LLMs, but haven't seen much news about embedding models.
Ask HN: Best Embedding Models?
1–10 of 20 posts
Re: Ask HN: Best Embedding Models?
#2I've liked qwen and embeddinggemma for local search. Qwen because 32K is enough to basically fit a whole page into the context window and embeddiggemma because it's crazy efficient.
Re: Ask HN: Best Embedding Models?
#3embeddings are easy to fine tune. Try modern bert.
Re: Ask HN: Best Embedding Models?
#4Benchmarks only paint part of the picture, but it's still a decent place to start looking into recent models:
Re: Ask HN: Best Embedding Models?
#5I’m partial to jina.ai — they have open models for code and prose, all easily runnable locally.
Re: Ask HN: Best Embedding Models?
#6who knows a tool for rug check in crypto
Re: Ask HN: Best Embedding Models?
#7Feels like embeddings are underrated compared to LLM's hype, but they doing great.
Re: Ask HN: Best Embedding Models?
#8gemma4
Re: Ask HN: Best Embedding Models?
#9I’ve been using MixedBread, which is a pretty old model at this point. Recently, I tried comparing it to some newer models and was disappointed that the results weren’t dramatically and uniformly better.
You probably can’t go wrong if you pick a recent one that scores decently well on benchmarks and is at the right price point (or memory requirement) for whatever you’re trying to do.
Re: Ask HN: Best Embedding Models?
#10E5 (Microsoft)