Open multimodal Llama model for long-context analysis and efficient agents
Details
| Field | Value |
|---|---|
| id | llama-4-scout-17b-instruct |
| family | llama |
| modality | text+image->text |
| context_length | 131072 |
| max_output_tokens | 2048 |
| release_date | 2025-04-05 |
| is_open_weights | yes |
| supports_tool_call | no |
| supports_reasoning | no |
| supports_structured_output | no |
| supports_attachment | yes |
| input_modalities | text, image |
| output_modalities | text |