# MinishLab/model2vec

Fast State-of-the-Art Static Embeddings

Repository: https://github.com/MinishLab/model2vec
Canonical: https://ross.abutalabs.com/products/model2vec
Homepage: https://minish.ai/packages/model2vec/introduction
Language: Python
License: MIT
License Family: permissive
Topics: embeddings, machine-learning, model2vec, nlp, python, sentence-transformers, ai, word-embeddings
Last push: 2026-08-26T19:12:12+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 55
- inputs: {"age_days": 776, "days_push": 7, "days_rel": 21, "gap_med": 6.0, "n_releases_24m": 27}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2186, forks 124 (observed 2026-08-28T04:06:23.646812+00:00)

## What it is
Model2Vec is a Python library that distills any sentence transformer into a tiny, fast static embedding model by computing one fixed vector per token and averaging them at inference time. It reduces model size up to 50x and speeds up inference up to 500x on CPU with only a small drop in quality.

## Use cases
- generate text embeddings fast on cpu
- distill a sentence transformer into a small static model
- build a lightweight retrieval or rag system
- classify documents at high throughput without gpu
- deduplicate or cluster large text datasets
- embed large corpora like wikipedia quickly
- reduce embedding model size for edge deployment

## When to choose
- you need very fast, cheap embeddings on cpu
- you want small models for retrieval, classification, or clustering
- you need to deploy embeddings without gpu or heavy dependencies
- you want sentence-transformers or langchain integration

## When to avoid
- you need state-of-the-art accuracy and can afford transformer inference
- your task depends on contextual token representations
- you need multilingual coverage not offered by available models

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, nlp, rag, search-engine
- domain: machine-learning
- platform: python, cross-platform
- tags: static-embeddings, sentence-transformers, embeddings, distillation, cpu-inference, text-classification, retrieval, natural-language-processing, retrieval-augmented-generation, search, cpu

## Member repositories
- MinishLab/model2vec (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:23.646812+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:47:53.859664+00:00, confidence not recorded.
  - readme: https://github.com/MinishLab/model2vec (fetched 2026-08-28T04:06:23.646812+00:00, sha 49e2beabb2f7)
  - homepage: https://minish.ai/packages/model2vec/introduction (fetched 2026-08-29T10:28:13.716536+00:00, sha 884cf4fbdb23)
  - site_page: https://minish.ai/about (fetched 2026-08-29T10:28:13.725421+00:00, sha 6332b2896728)
  - site_page: https://minish.ai/packages/model2vec/installation (fetched 2026-08-29T10:28:13.727355+00:00, sha 21a9aeffe4ea)
  - site_page: https://minish.ai/packages/semble/installation (fetched 2026-08-29T10:28:13.731063+00:00, sha 373938e60d5f)
  - site_page: https://minish.ai/packages/semhash/installation (fetched 2026-08-29T10:28:13.732740+00:00, sha ad1ab7983910)
  - site_page: https://minish.ai/packages/vicinity/installation (fetched 2026-08-29T10:28:13.734135+00:00, sha 4ed119eab51b)
  - registry_pypi: https://pypi.org/pypi/model2vec/json (fetched 2026-08-29T10:28:13.735535+00:00, sha c24bd616d293)
  - site_page: https://minish.ai/packages/model2vec/integrations (fetched 2026-08-29T10:28:13.729299+00:00, sha d24212c8593e)
- Data as of 2026-08-30T08:39:29.467469+00:00.