Qwen3.5-4B
Hugging Face (open weights) Open weights
The catch: A small model: fine for local and edge use but well behind the large Qwen models on hard tasks; the card advises at least 128K tokens of context for thinking.
| Access | Open weights |
|---|---|
| Free limits | Free to download and self-host; you pay only for your own compute. 4B dense, natively multimodal (image and video input); 262,144-token native context. Apache 2.0, no user or revenue cap. Smaller siblings: Qwen3.5-2B and Qwen3.5-0.8B. |
| Modality | text, code, image, video |
| Credit card | Not required |
| Commercial use | Allowed |
| Trains on your data | – |
| Licence or terms | Apache-2.0 |
| Context window | 262,144 tokens |
| Model id | Qwen/Qwen3.5-4B |
| Base URL | – |
| Last checked | 8 Oct 2026 |
How to use Qwen3.5-4B
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Quickstart
vllm serve Qwen/Qwen3.5-4B # then: curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{"model":"Qwen/Qwen3.5-4B","messages":[{"role":"user","content":"Hello"}]}'Paste into Claude Code
I want to run the open-weight model "Qwen3.5-4B" (Qwen/Qwen3.5-4B) 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
- A small model: fine for local and edge use but well behind the large Qwen models on hard tasks; the card advises at least 128K tokens of context for thinking.
- Apache-2.0 (licence tag and LICENSE 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 Qwen3.5-4B 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 Qwen3.5-4B commercially?
Yes, under Apache-2.0. Check the current terms before you ship.
How do I start with Qwen3.5-4B?
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Source: huggingface.co/Qwen/Qwen3.5-4B, checked 8 Oct 2026.