TaichuAI/ZDTaichu5.0-9B

TaichuAI releases ZDTaichu5.0-9B, a multimodal foundation model combining a Qwen3.5-9B backbone with a C-RADIOv4-H vision encoder. The model supports text, image, and video inputs for visual understanding, spatial reasoning, and agentic tool use. The model card documents architecture and usage, though independent verification of the reported benchmark scores remains pending.