TaichuAI Open-Sources ZDTaichu5.0-9B Spatial Multimodal Model

TaichuAI released the ZDTaichu5.0-9B model on Hugging Face with ~9 billion parameters: Qwen3.5-9B language backbone and C-RADIOv4-H vision encoder, context up to 128K tokens, support for text, images, and video. The model targets spatial perception, embodied tasks, and agent work, under the NVIDIA Open Model License.

Pandaily Open source

TaichuAI Open-Sources ZDTaichu5.0-9B Spatial Multimodal Model

~9B parameters, context up to 128K tokens, input text, images, video
Scores: ViewSpatial 62.50, RoboSpatial 56.00, TAU2-Bench 87.70, IFEval 93.70
Weights on Hugging Face under NVIDIA Open Model License with Qwen3.5 Apache-2.0 notices
For launch: custom vLLM 0.26.0 branch and Docker image with OpenAI-compatible API

#TaichuAI#Qwen#HuggingFace#VLLM

TaichuAI Open-Sources ZDTaichu5.0-9B Spatial Multimodal Model

OpenAI and Anthropic Negotiated Mutual AI Stress-Testing Deal

AI tag team Jev and Astra beat Minecraft in 8m43s for under $1

OpenAI details six real model misalignment incidents

Space Daily Published AI Slop Under Fake NASA and ESA Expert Bylines