Top open feature-extraction models
Models that extract embeddings and features for downstream tasks.
How this list works: ranked by Hugging Face downloads in the last 30 days, among models with 1,000+ downloads.
| # | Model | Author | Downloads (30 days) | Likes | Size | License | Commercial use | Runs on |
|---|---|---|---|---|---|---|---|---|
| 1 | bge-small-en-v1.5 | BAAI | 58.1M | 644 | – | MIT | Yes | CPU |
| 2 | bge-large-en-v1.5 | BAAI | 10M | 775 | – | MIT | Yes | CPU |
| 3 | bge-base-en-v1.5 | BAAI | 9M | 533 | – | MIT | Yes | CPU |
| 4 | Qwen3-Embedding-0.6B | Qwen | 8.6M | 1.3K | 600M | Apache 2.0 | Yes | GPU |
| 5 | multilingual-e5-large | intfloat | 6.7M | 1.3K | – | MIT | Yes | CPU |
| 6 | granite-embedding-small-english-r2 | ibm-granite | 5.7M | 105 | – | Apache 2.0 | Yes | GPU |
| 7 | all-MiniLM-L6-v2 | Xenova | 4.5M | 168 | – | Apache 2.0 | Yes | CPU |
| 8 | bge-small-zh-v1.5 | BAAI | 3.8M | 157 | – | MIT | Yes | GPU |
| 9 | bge-base-en | BAAI | 2.4M | 70 | – | MIT | Yes | CPU |
| 10 | bge-base-en-v1.5 | Xenova | 2.4M | 24 | – | MIT | Yes | CPU |
| 11 | bge-reranker-large | BAAI | 2.1M | 481 | – | MIT | Yes | CPU |
| 12 | Qwen3-Embedding-8B | Qwen | 2M | 834 | 8B | Apache 2.0 | Yes | GPU |
| 13 | mxbai-embed-large-v1 | mixedbread-ai | 2M | 839 | – | Apache 2.0 | Yes | CPU |
| 14 | jina-embeddings-v3 | jinaai | 1.7M | 1.2K | – | CC BY-NC 4.0 | No | CPU |
| 15 | Qwen3-Embedding-4B | Qwen | 1.7M | 340 | 4B | Apache 2.0 | Yes | GPU |
| 16 | multilingual-e5-large-instruct | intfloat | 1.7M | 651 | – | MIT | Yes | CPU |
| 17 | SapBERT-from-PubMedBERT-fulltext | cambridgeltl | 1.4M | 86 | – | Apache 2.0 | Yes | GPU |
| 18 | jina-embeddings-v2-small-en | jinaai | 1.2M | 154 | – | Apache 2.0 | Yes | CPU |
| 19 | w2v-bert-2.0 | 1.1M | 240 | – | MIT | Yes | GPU | |
| 20 | jina-embeddings-v5-omni-small | jinaai | 1M | 170 | – | CC BY-NC 4.0 | No | GPU |
| 21 | clap-htsat-unfused | laion | 1M | 89 | – | Apache 2.0 | Yes | GPU |
| 22 | 1 | unslothai | 930.9K | 1 | – | Not stated | Check the license | GPU |
| 23 | specter2_base | allenai | 905K | 54 | – | Apache 2.0 | Yes | GPU |
| 24 | repeat | unslothai | 791.7K | 0 | – | Not stated | Check the license | GPU |
| 25 | e5-mistral-7b-instruct-bnb-4bit | gabor-hosu | 780.3K | 11 | 7B | MIT | Yes | GPU |
Other model comparisons
Top open language modelsTop open image modelsTop open audio modelsTop open video modelsTop open embedding modelsTop open multimodal modelsTop open text-generation models (LLMs)Top open text-to-image modelsTop open text-to-speech modelsTop open speech-recognition modelsTop open sentence-similarity modelsTop open image-to-text modelsTop open vision-language modelsTop open image-classification modelsTop open image-segmentation modelsTop open object-detection modelsTop open depth-estimation modelsTop open audio-classification modelsTop open video-classification models