Top open embedding models
Embedding models for semantic search, retrieval, and similarity 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 | all-MiniLM-L6-v2 | sentence-transformers | 208.9M | 6.4K | – | Apache 2.0 | Yes | CPU |
| 2 | bge-small-en-v1.5 | BAAI | 58.1M | 644 | – | MIT | Yes | CPU |
| 3 | paraphrase-multilingual-MiniLM-L12-v2 | sentence-transformers | 45M | 1.5K | – | Apache 2.0 | Yes | CPU |
| 4 | bge-m3 | BAAI | 31.7M | 3.9K | – | MIT | Yes | CPU |
| 5 | all-mpnet-base-v2 | sentence-transformers | 18.1M | 1.4K | – | Apache 2.0 | Yes | CPU |
| 6 | nomic-embed-text-v1.5 | nomic-ai | 13.3M | 977 | – | Apache 2.0 | Yes | CPU |
| 7 | bge-large-en-v1.5 | BAAI | 10M | 775 | – | MIT | Yes | CPU |
| 8 | multilingual-e5-small | intfloat | 9.5M | 466 | – | MIT | Yes | CPU |
| 9 | paraphrase-multilingual-mpnet-base-v2 | sentence-transformers | 9.2M | 551 | – | Apache 2.0 | Yes | CPU |
| 10 | bge-base-en-v1.5 | BAAI | 9M | 533 | – | MIT | Yes | CPU |
| 11 | Qwen3-Embedding-0.6B | Qwen | 8.6M | 1.3K | 600M | Apache 2.0 | Yes | GPU |
| 12 | multilingual-e5-large | intfloat | 6.7M | 1.3K | – | MIT | Yes | CPU |
| 13 | multilingual-e5-base | intfloat | 6.3M | 410 | – | MIT | Yes | CPU |
| 14 | wespeaker-voxceleb-resnet34-LM | pyannote | 5.8M | 199 | – | CC BY 4.0 | Yes, with conditions | CPU or GPU |
| 15 | granite-embedding-small-english-r2 | ibm-granite | 5.7M | 105 | – | Apache 2.0 | Yes | GPU |
| 16 | all-MiniLM-L6-v2 | Xenova | 4.5M | 168 | – | Apache 2.0 | Yes | CPU |
| 17 | bge-base-en-v1.5-course-recommender-v5 | datasocietyco | 4.1M | 17 | – | Not stated | Check the license | GPU |
| 18 | bge-small-zh-v1.5 | BAAI | 3.8M | 157 | – | MIT | Yes | GPU |
| 19 | embeddinggemma-300m | 2.8M | 2K | 300M | Gemma license | Yes, with conditions | GPU | |
| 20 | all-MiniLM-L12-v2 | sentence-transformers | 2.8M | 346 | – | Apache 2.0 | Yes | CPU |
| 21 | all-distilroberta-v1 | sentence-transformers | 2.8M | 50 | – | Apache 2.0 | Yes | CPU |
| 22 | bge-base-en | BAAI | 2.4M | 70 | – | MIT | Yes | CPU |
| 23 | bge-base-en-v1.5 | Xenova | 2.4M | 24 | – | MIT | Yes | CPU |
| 24 | bge-reranker-large | BAAI | 2.1M | 481 | – | MIT | Yes | CPU |
| 25 | Qwen3-Embedding-8B | Qwen | 2M | 834 | 8B | Apache 2.0 | Yes | GPU |
Other model comparisons
Top open language modelsTop open image modelsTop open audio modelsTop open video 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 feature-extraction 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