55 days of daily snapshots

Trending open models

Ranked by 7-day download growth from our own nightly snapshots — history Hugging Face itself doesn't show.

#Model30dΔ 7dTrend
01 clap-htsat-unfused laion · feature-extraction 1.3 M ▲ 16.7%
02 specter2_base allenai · feature-extraction 1.2 M ▲ 9.0%
03 Qwen3-Embedding-8B Qwen · feature-extraction 2.6 M ▲ 8.6%
04 bge-base-en BAAI · feature-extraction 2.4 M ▲ 8.5%
05 all-MiniLM-L6-v2 Xenova · feature-extraction 3.0 M ▲ 6.7%
06 paraphrase-multilingual-MiniLM-L12-v2 Xenova · feature-extraction 672 K ▲ 6.7%
07 SapBERT-from-PubMedBERT-fulltext cambridgeltl · feature-extraction 1.5 M ▲ 6.1%
08 wavlm-large microsoft · feature-extraction 1.2 M ▲ 5.9%
09 conv-bert-base YituTech · feature-extraction 717 K ▲ 4.7%
10 bge-reranker-large BAAI · feature-extraction 2.8 M ▲ 3.9%
11 Qwen3-Embedding-0.6B Qwen · feature-extraction 8.6 M ▲ 3.8%
12 bge-small-zh-v1.5 BAAI · feature-extraction 5.1 M ▲ 2.4%
13 UAE-Large-V1 WhereIsAI · feature-extraction 1.1 M ▲ 2.4%
14 multilingual-e5-large intfloat · feature-extraction 7.2 M ▲ 2.3%
15 bge-base-zh-v1.5 BAAI · feature-extraction 812 K ▲ 2.1%
16 e5-mistral-7b-instruct-bnb-4bit gabor-hosu · feature-extraction 1.0 M ▲ 0.8%
17 repeat unslothai · feature-extraction 912 K ▲ 0.5%
18 bge-small-en-v1.5 BAAI · feature-extraction 64.5 M ▲ 0.2%
19 1 unslothai · feature-extraction 1.0 M ▲ 0.2%
20 Giga-Embeddings-instruct ai-sage · feature-extraction 696 K ▲ 0.1%
Snapshots taken nightly at 04:00 UTC from the public Hugging Face API. Also available as JSON: /api/v1/trending · methodology