Download
Qwen3-Embedding is a model series from the Qwen family designed specifically for text embedding and ranking tasks. It builds upon the Qwen3 base/dense models and offers several sizes (0.6B, 4B, 8B parameters), for both embedding and reranking, with high multilingual capability, long‐context understanding, and reasoning. It achieves state-of-the-art performance on benchmarks like MTEB (Multilingual Text Embedding Benchmark) and supports instruction-aware embedding (i.e. embedding task instructions along with queries) and flexible embedding/vector dimension definitions. It is meant for tasks such as text retrieval, classification, clustering, bitext mining, and code retrieval.
Features
- Multiple model sizes (0.6B, 4B, 8B) for embedding and reranking variants
- Multilingual support over 100 languages and dialects, including many low-resource ones; also supports programming languages in code retrieval tasks
- Supports long input context lengths (up to 32K tokens in many cases) for better handling of longer texts
- Instruction‐aware: you can augment input with task instructions to improve performance in specific domains or tasks
- Supports custom embedding dimensions via Matryoshka Representation Learning (MRL) in some variants
- High benchmark performance: e.g. the 8B embedding model ranks No.1 in MTEB multilingual leaderboard as of June 5, 2025; reranker models excel in retrieval contexts
Project Samples
License
Apache License V2.0Follow Qwen3 Embedding
nel_h2
MongoDB Atlas runs apps anywhere
MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Qwen3 Embedding!