Qwen vision-language model for visual reasoning, documents, and agent tasks
Details
| Field | Value |
|---|---|
| id | qwen3-vl-30b-a3b-instruct |
| family | qwen |
| modality | text+image->text |
| context_length | 262144 |
| max_output_tokens | 8192 |
| release_date | 2025-10-02 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | no |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | text, image |
| output_modalities | text |