This model is a ~14B parameter upscale of Qwen/Qwen3.5-9B. It has been merged with the base model to boost knowledge while keeping instruction following, because the base model was actually trained with some instruct-like examples.

You should fine-tune this model for it to be fully useable, while it has potential and all capabilities are still intact including vision, it currently faces looping issues, lower quality reasoning/COT. Due to mergekit not supporting qwen3.5, we used a custom layer-wise merge method.