Qwen vision-language model for visual reasoning, documents, and agent tasks
Details
| Field | Value |
|---|---|
| id | qwen2-5-vl-32b-instruct |
| family | qwen |
| modality | text+image->text |
| context_length | 131072 |
| max_output_tokens | 8192 |
| release_date | 2025-03-15 |
| 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 |