Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
Specifications
- Provider
- Qwen (Alibaba)
- Type
- Open-source / open-weight
- Modality
- text->text
- Context window
- 81,920
- Knowledge cutoff
- 2025-06-30
- Released
- August 28, 2025
Capabilities
Input: textOutput: textReasoning required
Strengths
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p
