Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning
Details
| Field | Value |
|---|---|
| id | Qwen/Qwen3-30B-A3B |
| family | qwen |
| modality | text->text |
| context_length | 40960 |
| max_output_tokens | 16384 |
| release_date | 2025-04-28 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | yes |
| supports_attachment | no |
| input_modalities | text |
| output_modalities | text |