Dense 27B vision-language model for coding, agent tasks, and image and video understanding
Details
| Field | Value |
|---|---|
| id | Qwen/Qwen3.8-27B-FP8 |
| family | qwen |
| modality | text+image->text |
| context_length | 262144 |
| max_output_tokens | 65536 |
| release_date | 2026-08-14 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | text, image |
| output_modalities | text |