Plain-English Summary
A large open embedding model for multilingual semantic search and retrieval.
Qwen3-Embedding-8B
A large open embedding model for multilingual semantic search and retrieval.
Qwen3 Embedding
Embedding
Open weights
Open weights: Yes
API: Yes and self-hosted
Technical Notes
8B embedding model designed for text retrieval, clustering, ranking, and multilingual semantic similarity.
Best For
High-quality open RAG, multilingual search, reranking pipelines
Watch Out For
Larger and slower than compact embedding models; requires vector infrastructure.
Model Specs
- Maker
- Alibaba Cloud / Qwen
- Country
- China
- Family
- Qwen3 Embedding
- Type
- Embedding
- Release date
- 2025-06-05
- Date confidence
- Exact
- Status
- Open weights
- Context window
- 32,768 tokens
- Max output
- Not listed
- Parameters
- 8B
- Active parameters
- 8B
- Architecture
- Dense embedding transformer
- Reasoning
- Not applicable
- Tool calling
- No
- Structured output
- Embedding vector
- API available
- Yes and self-hosted
- Open weights
- Yes
- Self-hostable
- Yes
- License
- Apache 2.0
- Inputs
- Text
- Outputs
- Embedding vector
- Approx. price
- See provider pricing
- How to access
- Provider website
- Model / API ID
- Qwen3-Embedding-8B
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Fine-tuning, selectable dimensions, self-hosting
- Completeness
- 95 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source