MODELS

Qwen/Qwen3-Embedding-0.6B

by Qwen

modellead-sourcehugging-face-popular-modelssource:github.comembeddingfeature-extractionretrievalrerankingqwenhugging-facegithub

Visit Website Documentation GitHub

Overview

Qwen3-Embedding-0.6B is a Qwen text embedding model listed for feature extraction and included in the Qwen3 Embedding model series.

Details

Qwen3-Embedding-0.6B is part of Qwen’s Qwen3 Embedding series. The official repository lists Qwen3-Embedding-0.6B in the model series and provides usage examples for Transformers, vLLM, and Sentence Transformers. Qwen’s announcement describes the series as released for text embedding, retrieval, and reranking, with models open-sourced on Hugging Face and ModelScope and code available on GitHub.

When to Use

Use it for text embedding or feature-extraction workflows where a Qwen3 Embedding model is suitable. Evaluate it for retrieval pipelines that need embeddings from the Qwen3 Embedding series. Review it alongside Qwen3 reranking options when building retrieval and reranking systems.

Getting Started

Open the Hugging Face model page for Qwen/Qwen3-Embedding-0.6B.
Review the official QwenLM/Qwen3-Embedding GitHub repository.
Follow the repository examples for Transformers
vLLM
or Sentence Transformers.
Read Qwen’s Qwen3 Embedding announcement for series-level context on embedding
retrieval
and reranking.

Key Features

•0.6B model in the Qwen3 Embedding series
•Listed on Hugging Face for feature extraction
•Official GitHub repository includes usage examples
•Series positioned by Qwen for text embedding
•retrieval
•and reranking

Capabilities

•feature-extraction
•text-embedding
•retrieval
•reranking-workflows

Last updated Jun 5, 2026