\n\n\n\n\n\nModel2Vec is a technique to turn any sentence transformer into a small, fast static embedding model. Model2Vec reduces model size by a factor up to 50 and makes models up to 500 times faster, with a small drop in performance. Our [best model](https://huggingface.co/minishlab/potion-base-32M) is the most performant static embedding model in the world. See our [results](results/README.md), read our [docs](https://minish.ai/packages/model2vec/introduction), or dive in to see how it works.\n\n
\n\n## Quickstart\n\nInstall the lightweight base package with:\n\n```bash\npip install model2vec\n```\n\nYou can start using Model2Vec by loading one of our [flagship models from the HuggingFace hub](https://huggingface.co/collections/minishlab/potion-6721e0abd4ea41881417f062). These models are pre-trained and ready to use. The following code snippet shows how to load a model and make embeddings, which you can use for any task, such as text classification, retrieval, clustering, or building a RAG system:\n```python\nfrom model2vec import StaticModel\n\n# Load a model from the HuggingFace hub (in this case the potion-base-32M model)\nmodel = StaticModel.from_pretrained(\"minishlab/potion-base-32M\")\n\n# Make embeddings\nembeddings = model.encode([\"It's dangerous to go alone!\", \"It's a secret to everybody.\"])\n\n# Make sequences of token embeddings\ntoken_embeddings = model.encode_as_sequence([\"It's dangerous to go alone!\", \"It's a secret to everybody.\"])\n```\nFor advanced usage, see our [inference docs](https://minish.ai/packages/model2vec/inference). Instead of using one of our models, you can also distill your own Model2Vec model from a Sentence Transformer model. First, install the `distillation` extras with:\n\n```bash\npip install model2vec[distill]\n```\n\n\nThen, you can distill a model in ~30 seconds on a CPU with the following code snippet:\n\n```python\nfrom model2vec.distill import distill\n\n# Distill a Sentence Transformer model, in this case the BAAI/bge-base-en-v1.5 model\nm2v_model = distill(model_","github_created_at":"2024-07-18T10:33:59+00:00","created_at":"2026-07-11T11:29:33.73064+00:00","updated_at":"2026-08-22T06:01:18.525936+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"embeddings","name":"embeddings"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"nlp","name":"nlp"},{"slug":"sentence-transformers","name":"sentence-transformers"},{"slug":"word-embeddings","name":"word-embeddings"}],"trust":{"provenance":{"is_fork":false,"github_id":830468922,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-22T06:01:17.735Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":1,"last_release_at":"2026-08-12T14:22:53Z","stars_delta_30d":22,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:29:35.173Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-22T06:01:18.242Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-22T06:01:18.242Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-22T06:01:18.242Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to create fast and efficient static embeddings for natural language processing (NLP) tasks.","Ideal if your project requires state-of-the-art static embeddings without the overhead of more complex models or frameworks."],"when_not_to_use":["Avoid using model2vec if dynamic embeddings are required, as it specializes in static embedding generation.","Not recommended for scenarios where you need a framework that supports real-time learning or continuous updates to embeddings as new data becomes available."],"source":"enrich:decision_facts","observed_at":"2026-07-12T08:10:07.685Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"model2vec is a Python tool for generating static embeddings with an emphasis on efficiency and state-of-the-art performance."}]}}
![\"Model2Vec](\"assets/images/model2vec_logo.png\"){kind=logo}
![\"Package](\"https://img.shields.io/pypi/v/model2vec?color=%23007ec6&label=pypi%20package\")
![\"Docs\"](\"https://img.shields.io/badge/docs-minish.ai-blue.svg\"){kind=icon}
![\"Downloads\"](\"https://static.pepy.tech/badge/model2vec\"){kind=icon}
\n ![\"Codecov\"](\"https://codecov.io/gh/MinishLab/model2vec/graph/badge.svg?token=21TWJ6B5ET\"){kind=icon}
\n ![\"Join](\"https://img.shields.io/badge/Join-Discord-5865F2?logo=discord&logoColor=white\"){kind=icon}
\n ![\"License](\"https://img.shields.io/badge/license-MIT-green\"){kind=icon}
\n ![Stars\"](\"https://img.shields.io/github/stars/minishlab/model2vec.svg\")
\n