# QwenLM/Qwen3-Embedding

Repository: https://github.com/QwenLM/Qwen3-Embedding
Canonical: https://ross.abutalabs.com/products/qwen3-embedding
Language: Python
License Family: other
Last push: 2025-09-30T06:10:27+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 44, release rhythm 35, longevity 32
- inputs: {"age_days": 454, "days_push": 337, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2016, forks 133 (observed 2026-08-28T04:06:05.601434+00:00)

## What it is
Qwen3-Embedding is a series of text embedding and reranking models (0.6B, 4B, 8B) built on Qwen3 foundation models, with a Python repository providing usage examples and tooling. The models support 100+ languages, instruction-aware embeddings, and flexible vector dimensions (MRL).

## Use cases
- generate text embeddings for semantic search
- rerank search results for retrieval pipelines
- build multilingual retrieval across 100+ languages
- retrieve code snippets by semantic similarity
- cluster and classify documents by embedding
- mine bitext pairs for translation

## When to choose
- you need state-of-the-art multilingual embeddings with MTEB-leading quality
- you want instruction-aware embeddings tunable per task
- you need flexible embedding dimensions for storage/latency tradeoffs
- you want to pair embedding and reranking models in a RAG pipeline

## When to avoid
- you need a tiny low-latency embedding model for CPU-only deployment
- you require a permissive license for commercial use without verification
- you just need a hosted embedding API without running models yourself

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, search-engine, rag, nlp
- domain: large-language-models
- platform: python, cross-platform
- tags: text-embedding, reranking, multilingual, mteb, sentence-embeddings, huggingface, natural-language-processing, search, retrieval-augmented-generation, gpu

## Member repositories
- QwenLM/Qwen3-Embedding (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:05.601434+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 2026-08-30T03:00:41.762698+00:00, confidence not recorded.
  - readme: https://github.com/QwenLM/Qwen3-Embedding (fetched 2026-08-28T04:06:05.601434+00:00, sha bf621e2ca0a4)
- Data as of 2026-08-30T08:39:29.467469+00:00.