Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Specifications
- Provider
- Qwen (Alibaba)
- Type
- Open-source / open-weight
- Modality
- text+image->text
- Context window
- 262,144
- Knowledge cutoff
- 2025-03-31
- Released
- September 23, 2025
Capabilities
Input: textInput: imageOutput: text
Strengths
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
