Open multimodal Llama model for long-context analysis and efficient agents
Details
| Field | Value |
|---|---|
| id | meta-llama/Llama-4-Scout-17B-16E-Instruct |
| family | llama |
| modality | text+image->text |
| context_length | 327680 |
| max_output_tokens | 16384 |
| release_date | 2025-04-05 |
| 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 |