Zhipu AI Open-Sources 9B Vision Model with 'Thinking' Mode

Zhipu AI has released a new open-source vision-language model, GLM-4.1V-9B-Thinking. At 9 billion parameters, the model is designed to interpret and reason about visual inputs, marking another significant entry into the competitive field of multimodal AI.

The model's most distinct feature is its explicit "thinking" mode. This enables a chain-of-thought process, where the model generates intermediate reasoning steps before arriving at a final answer. For developers and researchers, this transparency can make it easier to understand and debug the model's conclusions on complex visual question-answering tasks.

Permissive Licensing for Broader Use

Perhaps most notably for the open-source community, Zhipu AI has released the model under the highly permissive MIT license. This choice removes significant barriers to adoption, allowing for broad use in both commercial applications and academic research. The move encourages wider experimentation and integration compared to models with more restrictive licenses.

The complete model weights and details are available for download on Hugging Face. This release provides developers with a powerful and transparent tool for building applications that require a sophisticated understanding of both language and imagery.