Qwen3-Embedding-8B
Hugging Face (Qwen) Open weights
The catch: Queries need a one-line task instruction for best results (the card reports a 1-5% gain), and it needs transformers 4.51 or newer.
| Access | Open weights |
|---|---|
| Free limits | Free to download and self-host; you pay only for your own compute. 8B parameters; embeddings up to 4096 dims (any size from 32 to 4096, MRL); 32K-token input; 100+ languages. Smaller sizes, same licence and 32K input: Qwen3-Embedding-4B (2560 dims) and Qwen3-Embedding-0.6B (1024 dims). |
| 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-8B |
| Base URL | – |
| Last checked | 2 Oct 2026 |
How to use Qwen3-Embedding-8B
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Quickstart
ollama pull qwen3-embedding:8b
Paste into Claude Code
I want to run the open-weight model "Qwen3-Embedding-8B" (Qwen/Qwen3-Embedding-8B) 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
- Queries need a one-line task instruction for best results (the card reports a 1-5% gain), and it needs transformers 4.51 or newer.
- Apache License 2.0 (LICENSE file and licence tag on huggingface.co/Qwen/Qwen3-Embedding-8B); commercial use allowed, no user cap.
- Free to run means you pay for the GPUs, the serving stack and the on-call.
Questions
Is Qwen3-Embedding-8B 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-8B commercially?
Yes, under Apache-2.0. Check the current terms before you ship.
How do I start with Qwen3-Embedding-8B?
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Source: huggingface.co/Qwen/Qwen3-Embedding-8B, checked 2 Oct 2026.