OpenSpatial-Qwen3-VL-8B

OpenSpatial-Qwen3-VL-8B is an OpenSpatial model fine-tuned for spatial understanding and reasoning. This repository contains full, inference-ready model weights.

• Project: https://github.com/VINHYU/OpenSpatial
• Paper: https://arxiv.org/abs/2604.07296
• Training data: https://huggingface.co/datasets/jdopensource/JoyAI-Image-OpenSpatial
• Base model: https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct

Loading

Use transformers >=4.57.0 for this checkpoint.

from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

model_id = "VINHYU/OpenSpatial-Qwen3-VL-8B"
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_id, torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained(model_id)

Please refer to the OpenSpatial repository and the base model repository for full usage instructions, limitations, and license terms.