logoalt Hacker News

kaycebasquesyesterday at 8:31 PM2 repliesview on HN

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?


Replies

intalentiveyesterday at 9:57 PM

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.

nijaruyesterday at 10:06 PM

For something under 100 MB, this is probably the strongest option right now.

https://huggingface.co/MongoDB/mdbr-leaf-ir