---
license: apache-2.0
base_model:
- rsoohyun/SpatialBlock-3B-reason
language:
- en
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- text-generation-inference
- llama-cpp
---

# **SpatialBlock-3B-reason-GGUF**

> **SpatialBlock-3B-reason** is an open-source multimodal model released on Hugging Face by [rsoohyun](https://huggingface.co/rsoohyun) under the Apache-2.0 license, developed to enhance spatial intelligence in Large Vision-Language Models (LVLMs). Based on the `Qwen/Qwen2.5-VL-3B-Instruct` base architecture and supported by the Hugging Face `transformers` library via the `image-text-to-text` pipeline, this checkpoint is fine-tuned on the synthetic `SpatialBlock-15k` dataset as presented in the paper *SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem*. It specializes in reasoning through and directly predicting solutions to intricate spatial challenges—including 3D-to-2D projection, viewpoint transformation, and structural combination—with complete training methodology, evaluation metrics, and companion models accessible via its [GitHub repository](https://github.com/rsoohyun/SpatialBlock).

## Model Files

   File Name | Quant Type | File Size | File Link |
 |-----------|------------|-----------|-----------|
 | SpatialBlock-3B-reason.BF16.gguf | BF16 | 6.8 GB | [Download](https://huggingface.co/prithivMLmods/SpatialBlock-3B-reason-GGUF/blob/main/SpatialBlock-3B-reason.BF16.gguf) |
 | SpatialBlock-3B-reason.Q4_K_M.gguf | Q4_K_M | 2.1 GB | [Download](https://huggingface.co/prithivMLmods/SpatialBlock-3B-reason-GGUF/blob/main/SpatialBlock-3B-reason.Q4_K_M.gguf) |
 | SpatialBlock-3B-reason.Q5_K_M.gguf | Q5_K_M | 2.44 GB | [Download](https://huggingface.co/prithivMLmods/SpatialBlock-3B-reason-GGUF/blob/main/SpatialBlock-3B-reason.Q5_K_M.gguf) |
 | SpatialBlock-3B-reason.mmproj-bf16.gguf | mmproj-bf16 | 1.34 GB | [Download](https://huggingface.co/prithivMLmods/SpatialBlock-3B-reason-GGUF/blob/main/SpatialBlock-3B-reason.mmproj-bf16.gguf) |

## llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp