AlibabaQwen3.5
Qwen3.5-4B
A compact four-billion-parameter vision-language release.
Practical use
Practical guidance. For a local document assistant, assess extraction accuracy before writing long prompts. Short, explicit field definitions can make failures easier to identify and correct.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | Qwen/Qwen3.5-4B |
| Architecture | Four billion parameters; 32 layers.Qwen3.5-4B model card |
| Context | 262,144 native tokens; the card documents extension to about one million.Qwen3.5-4B model card |
| Licence | Apache 2.0.Qwen3.5-4B model card |
Related models
- Qwen3.5-397B-A17B
Alibaba · Qwen3.5
The large published vision-language checkpoint behind hosted Qwen3.5 Plus.
Launch date not confirmedDownloadable - Qwen3.5-122B-A10B
Alibaba · Qwen3.5
A mid-sized sparse release in the Qwen3.5 vision-language family.
Launch date not confirmedDownloadable - Qwen3.5-27B
Alibaba · Qwen3.5
A dense Qwen3.5 release with image understanding.
Launch date not confirmedDownloadable