Hugging Face's logo

remyxai
/
SpaceQwen2.5-VL-3B-Instruct

Image-Text-to-Text
Transformers
Safetensors
GGUF
English
qwen2_5_vl
remyx
vqasynth
spatial-reasoning
multimodal
vlm
vision-language
robotics
distance-estimation
embodied-ai
quantitative-spatial-reasoning
conversational
Eval Results
text-generation-inference
Model card Files Community
2
SpaceQwen2.5-VL-3B-Instruct / README.md
nielsr's picture
nielsr HF Staff
Improve model card with paper link and clarify metadata
df12433 verified
preview code
|
raw
history blame
8.39 kB
metadata
base_model:
  - Qwen/Qwen2.5-VL-3B-Instruct
datasets:
  - remyxai/OpenSpaces
language:
  - en
library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
tags:
  - remyx
  - vqasynth
  - spatial-reasoning
  - multimodal
  - vlm
  - vision-language
  - robotics
  - distance-estimation
  - embodied-ai
  - quantitative-spatial-reasoning
new_version: remyxai/SpaceThinker-Qwen2.5VL-3B
model-index:
  - name: SpaceQwen2.5-VL-3B-Instruct
    results:
      - task:
          type: visual-question-answering
          name: Spatial Reasoning
        dataset:
          name: 3DSRBench
          type: benchmark
        metrics:
          - type: success_rate
            value: 0.515
            name: Overall Success Rate
          - type: success_rate
            value: 0.5
            name: Overall Success Rate
          - type: success_rate
            value: 0.3045
            name: Overall Success Rate
          - type: success_rate
            value: 0.5767
            name: Overall Success Rate
          - type: success_rate
            value: 0.3663
            name: Overall Success Rate
          - type: success_rate
            value: 0.33
            name: Overall Success Rate
          - type: success_rate
            value: 0.4392
            name: Overall Success Rate
          - type: success_rate
            value: 0.6554
            name: Overall Success Rate
          - type: success_rate
            value: 0.2615
            name: Overall Success Rate
          - type: success_rate
            value: 0.2322
            name: Overall Success Rate
          - type: success_rate
            value: 0.7373
            name: Overall Success Rate
          - type: success_rate
            value: 0.5179
            name: Overall Success Rate
          - type: success_rate
            value: 0.4879
            name: Overall Success Rate

SpaceQwen2.5-VL-3B-Instruct

The model was presented in the paper OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models. More information can be found at the project page.

  • Model Type: Multimodal, Vision-Language Model
  • Architecture: Qwen2.5-VL-3B-Instruct
  • Model Size: 3.75B parameters (FP16)
  • Finetuned from: Qwen/Qwen2.5-VL-3B-Instruct
  • Finetune Strategy: LoRA (Low-Rank Adaptation)
  • License: Apache-2.0

Model Overview

This model uses data synthesis techniques and publicly available models to reproduce the work described in SpatialVLM to enhance the spatial reasoning of multimodal models. With a pipeline of expert models, we can infer spatial relationships between objects in a scene to create a VQA dataset for spatial reasoning.

Running SpaceQwen2.5-VL-3B-Instruct

Ollama

To launch with ollama, run:

ollama run hf.co/remyxai/SpaceQwen2.5-VL-3B-Instruct:latest

Transformers

Install qwen dependencies:

pip install qwen-vl-utils[decord]==0.0.8

To run inference on a sample image:

from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "remyxai/SpaceQwen2.5-VL-3B-Instruct", torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("remyxai/SpaceQwen2.5-VL-3B-Instruct")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://raw.githubusercontent.com/remyxai/VQASynth/refs/heads/main/assets/warehouse_sample_2.jpeg",
            },
            {"type": "text", "text": "What is the height of the man in the red hat in feet?"},
        ],
    }
]

# Preparation for inference
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

GGUF

Or run SpaceQwen2.5-VL-3B-Instruct using llama.cpp:

./llama-qwen2vl-cli -m /path/to/SpaceQwen2.5-VL-3B-Instruct/SpaceQwen2.5-VL-3B-Instruct-F16.gguf \
                    --mmproj /path/to/SpaceQwen2.5-VL-3B-Instruct/spaceqwen2.5-vl-3b-instruct-vision.gguf \
                    -p "What's the height of the man in the red hat?" \
                    --image /path/to/warehouse_sample_2.jpeg --threads 24 -ngl 99

Dataset & Training

SpaceQwen2.5-VL-3B-Instruct uses LoRA to fine-tune Qwen2.5-VL-3B-Instruct on the OpenSpaces dataset.

Dataset Summary:

  • ~10k synthetic spatial reasoning traces

  • Question types: spatial relations (distances (units), above, left-of, contains, closest to)

  • Format: image (RGB) + question + answer

  • Dataset: OpenSpaces

  • Code: VQASynth

  • Reference: SpatialVLM

Scripts for LoRA SFT available at trl

Model Evaluation

SpatialScore

SpaceQwen shines in the 3D positional relations categories of the SpatialScore-Hard comparison featured in the table below:

image/png

Read more about the comprehensive spatial reasoning benchmark: SpatialScore.

The following chart compares performance between SpaceQwen and SpaceThinker on the SpatialScore benchmarks sources.

SpaceQwen_v_SpaceThinker

OmniSpatial

OmniSpatial is another comprehensive spatial reasoning benchmark that assesses dynamic reasoning, complex spatial logic, spatial interaction, and perspective-taking capabilities. image/png

Learn more about OmniSpatial.

⚠️ Limitations & Ethical Considerations

  • Performance may degrade in cluttered environments or camera perspective.
  • This model was fine-tuned using synthetic reasoning over an internet image dataset.
  • Multimodal biases inherent to the base model (Qwen2.5-VL) may persist.
  • Not intended for use in safety-critical or legal decision-making.

Users are encouraged to evaluate outputs critically and consider fine-tuning for domain-specific safety and performance.

Citation 

@article{chen2024spatialvlm,
  title = {SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities},
  author = {Chen, Boyuan and Xu, Zhuo and Kirmani, Sean and Ichter, Brian and Driess, Danny and Florence, Pete and Sadigh, Dorsa and Guibas, Leonidas and Xia, Fei},
  journal = {arXiv preprint arXiv:2401.12168},
  year = {2024},
  url = {https://arxiv.org/abs/2401.12168},
}

@misc{qwen2.5-VL,
    title = {Qwen2.5-VL},
    url = {https://qwenlm.github.io/blog/qwen2.5-vl/},
    author = {Qwen Team},
    month = {January},
    year = {2025}
}

@article{wu2025spatialscore,
    author    = {Wu, Haoning and Huang, Xiao and Chen, Yaohui and Zhang, Ya and Wang, Yanfeng and Xie, Weidi},
    title     = {SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding},
    journal   = {arXiv preprint arXiv:2505.17012},
    year      = {2025},
}

@article{omnispatial25,
  title   = {OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models},
  author  = {Mengdi Jia and Zekun Qi and Shaochen Zhang and Wenyao Zhang and Xinqiang Yu and Jiawei He and He Wang and Li Yi},
  journal = {arXiv preprint arXiv:2506.03135},
  year = {2025}
}