Spaceom GGUF

🚀 SpaceOm-GGUF

SpaceOm-GGUF is a model designed for visual - question - answering tasks, excelling in spatial reasoning. It enhances performance through specific fine - tuning and additional datasets, offering valuable insights for multimodal and robotics applications.

🚀 Quick Start

This section doesn't provide specific quick - start steps. If you want to use the SpaceOm - GGUF model, you can refer to the official documentation of the llama.cpp library.

✨ Features

• Enhanced Fine - Tuning: Adds the target module o_proj in LoRA fine - tuning, inspired by relevant research, which is beneficial for reasoning models.
• Rich Datasets: Utilizes the SpaceOm [dataset](https://huggingface.co/datasets/salma - remyx/SpaceOm) for longer reasoning traces and the Robo2VLM - Reasoning [dataset](https://huggingface.co/datasets/salma - remyx/Robo2VLM - Reasoning) for more robotics domain and MCVQA examples.
• Improved Reasoning Ability: Incorporates longer reasoning traces in training data to help the model use more tokens in reasoning.

📚 Documentation

Model Overview

SpaceOm improves over SpaceThinker by:

• Adding the target module o_proj in LoRA fine - tuning. The choice of including o_proj is inspired by the study here, which emphasizes the importance of this module in reasoning models.
• Using the SpaceOm [dataset](https://huggingface.co/datasets/salma - remyx/SpaceOm) for longer reasoning traces. The reasoning traces in the SpaceThinker dataset average ~200 "thinking" tokens, and now longer reasoning traces are included in the training data to assist the model in using more tokens for reasoning.
• Employing the Robo2VLM - Reasoning [dataset](https://huggingface.co/datasets/salma - remyx/Robo2VLM - Reasoning) for more robotics domain and MCVQA examples. To improve alignment for robotics applications, it is trained with synthetic reasoning traces derived from the Robo2VLM - 1 [dataset](https://huggingface.co/datasets/keplerccc/Robo2VLM - 1).

Model Evaluation

SpatialScore - 3B and 4B models

See [all results](https://huggingface.co/datasets/salma - remyx/SpaceOm_SpatialScore) for evaluating SpaceOm on the SpatialScore benchmark. Compared to SpaceQwen, this model outperforms in all categories.

And comparing to SpaceThinker:

SpaCE - 10 Benchmark Comparison

[](https://colab.research.google.com/drive/1YpIOjJFZ - Zaomg77ImeQHSqYBLB8T1Ce?usp = sharing)

This table compares SpaceOm evaluated using GPT scoring against several top models from the SpaCE - 10 benchmark leaderboard. Top scores in each category are bolded.

Legend:

• EQ: Entity Quantification
• SQ: Scene Quantification
• SA: Size Assessment
• OO: Object - Object spatial relations
• OS: Object - Scene spatial relations
• EP: Entity Presence
• FR: Functional Reasoning
• SP: Spatial Planning

⚠️ Important Note

Scores for SpaceOm are generated via gpt_eval_score on single - choice (*-single) versions of the SpaCE - 10 benchmark tasks. Other entries reflect leaderboard accuracy scores from the official SpaCE - 10 evaluation table.

Read more about the SpaCE - 10 benchmark

Limitations

• 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.

💡 Usage Tip

Users are encouraged to evaluate outputs critically and consider fine - tuning for domain - specific safety and performance. Distances estimated using autoregressive transformers may help in higher - order reasoning for planning and behavior but may not be suitable replacements for measurements taken with high - precision sensors, calibrated stereo vision systems, or specialist monocular depth estimation models capable of more accurate, pixel - wise predictions and real - time 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}
}

@misc{vl-thinking2025,
  title={SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models },
  author={Hardy Chen and Haoqin Tu and Fali Wang and Hui Liu and Xianfeng Tang and Xinya Du and Yuyin Zhou and Cihang Xie},
  year = {2025},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/UCSC-VLAA/VLAA-Thinking}},
}


@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{gong2025space10,
  title     = {SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence},
  author    = {Ziyang Gong and Wenhao Li and Oliver Ma and Songyuan Li and Jiayi Ji and Xue Yang and Gen Luo and Junchi Yan and Rongrong Ji},
  journal   = {arXiv preprint arXiv:2506.07966},
  year      = {2025},
  url       = {https://arxiv.org/abs/2506.07966}
}