Open multimodal Gemma instruction model for efficient text generation and image understanding
Details
| Field | Value |
|---|---|
| id | google/gemma-3-4b-it |
| family | gemma |
| modality | text+image->text |
| context_length | 131072 |
| max_output_tokens | 131072 |
| quantization | bf16 |
| knowledge_cutoff | 2024-08 |
| release_date | 2025-03-12 |
| 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 |