AlibabaQwen Embedding
Qwen3-Embedding-4B
This instruction-aware embedding checkpoint supports more than 100 languages and a 32,000-token context.
Practical use
Practical guidance. Use this size as a middle comparison point for multilingual retrieval. Include queries whose wording differs from the source documents, and keep the same query instruction for every candidate model.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | Qwen/Qwen3-Embedding-4B |
| Vector dimensions | User-selected dimensions from 32 to 2560.Qwen3-Embedding-4B model card |
| Scope | Text, cross-language and code retrieval.Qwen3-Embedding-4B model card |
| Licence | Apache 2.0.Qwen3-Embedding-4B model card |
Related models
- Qwen3-Embedding-8B
Alibaba · Qwen Embedding
Eight-billion-parameter multilingual embedding model with task instructions and a 32,000-token context.
Launch date not confirmedDownloadable - Qwen3-Embedding-0.6B
Alibaba · Qwen Embedding
A 600-million-parameter text embedding model with task instructions, over 100 languages and a 32,000-token context.
Launch date not confirmedDownloadable - Qwen3.7 Text Embedding
Alibaba · Qwen Embedding
Hosted text embedding family with standard and Flash variants and inputs up to 131,072 tokens.
Launch date not confirmedAPI