Qwen3-Embedding 0.6B
Hugging Face (open weights) Open weights
The catch: Lower retrieval quality than the 4B and 8B sizes.
| Access | Open weights |
|---|---|
| Free limits | Free to download and self-host; you pay only for your own compute. 0.6B text embedding model; up to 1024 dimensions (any size from 32); 32K-token input; 100+ languages. Runs on CPU or a small GPU. |
| Modality | embeddings |
| Credit card | Not required |
| Commercial use | Allowed |
| Trains on your data | – |
| Licence or terms | Apache-2.0 |
| Context window | 32,768 tokens |
| Model id | Qwen/Qwen3-Embedding-0.6B |
| Base URL | – |
| Last checked | 8 Oct 2026 |
How to use Qwen3-Embedding 0.6B
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Quickstart
pip install -U sentence-transformers && python -c "from sentence_transformers import SentenceTransformer; print(SentenceTransformer('Qwen/Qwen3-Embedding-0.6B').encode(['hello']).shape)"Paste into Claude Code
I want to run the open-weight model "Qwen3-Embedding 0.6B" (Qwen/Qwen3-Embedding-0.6B) for my project. Please: 1. Check the model card and tell me the hardware it needs and the simplest way to serve it (vLLM, SGLang, Ollama or a hosted endpoint). 2. Give me a minimal working setup and a test request. 3. Tell me the licence terms for commercial use. 4. If a cheaper or smaller variant would do the job, mention it.
Before you ship on it
- Lower retrieval quality than the 4B and 8B sizes.
- Apache-2.0 (licence tag on the HF repo): use, modify, distribute and sell, including commercially; keep the licence and notices when you redistribute.
- Free to run means you pay for the GPUs, the serving stack and the on-call.
Questions
Is Qwen3-Embedding 0.6B free?
Yes. Open weights offers it as open weights, with these limits: Self-host free · Apache-2.0. No credit card is needed.
Can I use Qwen3-Embedding 0.6B commercially?
Yes, under Apache-2.0. Check the current terms before you ship.
How do I start with Qwen3-Embedding 0.6B?
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Source: huggingface.co/Qwen/Qwen3-Embedding-0.6B, checked 8 Oct 2026.