QwenLM/Qwen3-Embedding
A text embedding and reranking model series from the Qwen3 family providing 0.6B to 8B parameter models for retrieval and ranking tasks.
Not currently ranked — collecting fresh signals.
star history
Qwen3 Embedding is a series of embedding and reranking models designed for text retrieval, classification, clustering, and bitext mining. The models inherit multilingual capabilities and long-text understanding from the Qwen3 foundation models. Available in 0.6B, 4B, and 8B parameter sizes, they achieve state-of-the-art performance on MTEB benchmarks, ranking #1 on the multilingual leaderboard as of June 2025.
Frequently asked
- What is QwenLM/Qwen3-Embedding?
- A text embedding and reranking model series from the Qwen3 family providing 0.6B to 8B parameter models for retrieval and ranking tasks.
- Is Qwen3-Embedding open source?
- Yes — QwenLM/Qwen3-Embedding is an open-source project tracked on heatdrop.
- What language is Qwen3-Embedding written in?
- QwenLM/Qwen3-Embedding is primarily written in Python.
- How popular is Qwen3-Embedding?
- QwenLM/Qwen3-Embedding has 2k stars on GitHub.
- Where can I find Qwen3-Embedding?
- QwenLM/Qwen3-Embedding is on GitHub at https://github.com/QwenLM/Qwen3-Embedding.