[Zidong Taichu open source ZDTaichu5.0-9B: A universal multi-modal large model with leading spatial embodiment capabilities within 10B parameters] On September 15th, Zidong Taichu officially open sourced ZDTaichu5.0-9B. The model volume is adapted to the implementation requirements. In the general multi-modal large model with less than 10B parameters, spatial understanding and embodied capabilities are outstanding, the general multi-modal capabilities remain at a high level, and the full-link capabilities such as perception, cognition, decision-making and action are fully covered. What is more noteworthy is that this open source not only opens up the model weights, but also discloses detailed data production plans, which have been verified in real physical scenarios such as scientific research automation and intelligent manufacturing. This open source means that domestic multi-modal large models are moving from "understanding the digital world" to "understanding and acting in the physical world."