Qwen 3.5 0.8B
Lightest Qwen 3.5 (~1.6 GB VRAM). Low-resource.
- Runs on
- Your device, in the browser
- Size
- 0.8B
- Best for
- Coding and deep reasoning
Qwen 3.5 0.8B runs in your browser, on your own device. The model downloads once and stays there; what you type is never sent to Alibaba or to us , and no API key is involved.
Context window
262,144 tokens
≈ 197,000 words · about 790 pages
the model's own limit — how much your device can hold depends on its memory
Modalities
- TextInput and output
- ImageNot supported
- AudioNot supported
- VideoNot supported
Features
- StreamingSupported
- Function callingNot supported
- Structured outputsSupported
- Fine-tuningNot supported
Where it comes from
| Model card | Alibaba's card for Qwen 3.5 0.8B |
|---|---|
| Weights | The build your browser downloads |
| Runtime | WebLLM |
Ready to try it?
Polymeti is currently invite-only.
Log inRuns on your device · No API key · Your chats stay in your browser