---
license: apache-2.0
base_model:
- FireRedTeam/FireRed-OCR
language:
- en
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- text-generation-inference
- llama.cpp
---

# **FireRed-OCR-GGUF** 

> FireRed-OCR from FireRedTeam is a specialized framework that transforms general Large Vision-Language Models into pixel-precise structural document parsing experts, tackling "Structural Hallucination" issues like disordered rows and invented formulas through a shift to "structural engineering" paradigms, achieving SOTA 92.94% on OmniDocBench v1.5—vastly outperforming DeepSeek-OCR 2, OCRVerse, and giants like Gemini-3.0 Pro or Qwen3-VL-235B. Its key innovations include Format-Constrained GRPO (Group Relative Policy Optimization) for enforcing syntactic validity (no unclosed tables or invalid LaTeX), a "Geometry + Semantics" data factory with geometric clustering and multi-dimensional tagging for balanced long-tail layouts, and a progressive pipeline: multi-task pre-alignment for spatial grounding, specialized SFT for standardized full-image Markdown output, and GRPO self-correction via RL. Demonstrating in-the-wild robustness on FireRedBench complex layouts over traditional systems like PaddleOCR, it excels in high-fidelity parsing of tables, equations, forms, and multi-column documents for real-world automation.

## Model Files

| File Name | Quant Type | File Size | File Link |
| - | - | - | - |
| FireRed-OCR.BF16.gguf | BF16 | 3.45 GB | [Download](https://huggingface.co/prithivMLmods/FireRed-OCR-GGUF/blob/main/FireRed-OCR.BF16.gguf) |
| FireRed-OCR.F16.gguf | F16 | 3.45 GB | [Download](https://huggingface.co/prithivMLmods/FireRed-OCR-GGUF/blob/main/FireRed-OCR.F16.gguf) |
| FireRed-OCR.F32.gguf | F32 | 6.89 GB | [Download](https://huggingface.co/prithivMLmods/FireRed-OCR-GGUF/blob/main/FireRed-OCR.F32.gguf) |
| FireRed-OCR.Q8_0.gguf | Q8_0 | 1.83 GB | [Download](https://huggingface.co/prithivMLmods/FireRed-OCR-GGUF/blob/main/FireRed-OCR.Q8_0.gguf) |
| FireRed-OCR.mmproj-bf16.gguf | mmproj-bf16 | 823 MB | [Download](https://huggingface.co/prithivMLmods/FireRed-OCR-GGUF/blob/main/FireRed-OCR.mmproj-bf16.gguf) |
| FireRed-OCR.mmproj-f16.gguf | mmproj-f16 | 823 MB | [Download](https://huggingface.co/prithivMLmods/FireRed-OCR-GGUF/blob/main/FireRed-OCR.mmproj-f16.gguf) |
| FireRed-OCR.mmproj-f32.gguf | mmproj-f32 | 1.63 GB | [Download](https://huggingface.co/prithivMLmods/FireRed-OCR-GGUF/blob/main/FireRed-OCR.mmproj-f32.gguf) |
| FireRed-OCR.mmproj-q8_0.gguf | mmproj-q8_0 | 445 MB | [Download](https://huggingface.co/prithivMLmods/FireRed-OCR-GGUF/blob/main/FireRed-OCR.mmproj-q8_0.gguf) |

## Quants Usage 

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)