{"id":"e74e1315-fd3e-43eb-a061-5e698b59e9d5","slug":"hf-model-ox-pixl-spatialthinker-7b-11it4gw-p","name":"SpatialThinker-7B","description":"Hugging Face model OX-PIXL/SpatialThinker-7B. Task: image text to text. 239 downloads. 2 likes.","capabilities":["safetensors","qwen2_5_vl","spatial-reasoning","multimodal","vision-language","scene-graph","reinforcement-learning","image-text-to-text","conversational","en","arxiv:2511.07403","base_model:Qwen/Qwen2.5-VL-7B-Instruct","base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":39.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:03.244Z"}