How to use from
SGLang
Install from pip and serve model
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "jankin123/3DThinker-Mindcube" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jankin123/3DThinker-Mindcube",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'
Use Docker images
docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "jankin123/3DThinker-Mindcube" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jankin123/3DThinker-Mindcube",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'
Quick Links

3DThinker-Mindcube

This repository contains the stage 1 model checkpoint for 3DThinker, as presented in the paper Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views.

3DThinker is a framework that enables Vision-Language Models (VLMs) to exploit geometric information within images for 3D spatial reasoning, simulating human-like spatial imagination without requiring explicit 3D prior inputs or labeled 3D training data.

Introduction

  • The model was trained on Mindcube_Train and tested on MindCube-Tiny.
  • This model corresponds to stage 1 training (supervised alignment of 3D latents) of Qwen2.5-3B-VL.
  • Note that Tab. 2 in the paper is trained on a different training data configuration.

Bibtex

If you find 3DThinker helpful for your work, please cite:

@article{chen2025think,
  title={Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views},
  author={Chen, Zhangquan and Zhang, Manyuan and Yu, Xinlei and Luo, Xufang and Sun, Mingze and Pan, Zihao and Feng, Yan and Pei, Peng and Cai, Xunliang and Huang, Ruqi},
  journal={arXiv preprint arXiv:2510.18632},
  year={2025}
}
Downloads last month
45
Safetensors
Model size
4B params
Tensor type
BF16
·
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jankin123/3DThinker-Mindcube

Finetuned
(874)
this model

Paper for jankin123/3DThinker-Mindcube