richardyoung/ xiaomi-ocr-0:Q6_K

2 yesterday

Xiaomi-OCR-0 (0.8B): document parsing, OCR Q&A and key-info extraction. #1 on Real5-OmniDocBench. Images work.

vision 
ollama run richardyoung/xiaomi-ocr-0:Q6_K

Details

yesterday

03500222b092 · 852MB

model
qwen35
·
773M
·
Q6_K
projector
clip
·
101M
·
F16

Readme

Xiaomi-OCR-0

Xiaomi-OCR-0 (0.8B): document parsing, OCR Q&A and key-info extraction. #1 on Real5-OmniDocBench. Images work.

🚀 Overview

GGUF build of SeerRay-Lab/Xiaomi-OCR-0, a unified 0.8B OCR model built on Qwen3.5-0.8B-Base for document parsing, OCR-centric question answering and key information extraction. It ships with its vision projector, so image input works in Ollama.

Prompts (from the model card): document → Extract all information from the main body of the document image and represent it in markdown format, ignoring headers and footers. Tables should be expressed in OTSL format, formulas in the document should be represented using LATEX format, and the parsing should be organized according to the reading order. · text region → Extract the text in the image. · table → Parse the table in the image into OTSL. · formula → Identify the formula in the image and represent it using LATEX format. · KIE → Extract key information in the image followed by your JSON schema. The authors’ own image preprocessing and decoding settings are in their repo’s OLLAMA.md; results here use the GGUF as-is.

🎯 Key Features

  • 95.24 on Real5-OmniDocBench (#1) and 96.83 on OmniDocBench v1.6 (#2), per the authors
  • Robust on scanned, warped, photographed and skewed pages
  • Formulas (LaTeX), tables (OTSL) and JSON key-information extraction
  • Only 0.8B parameters
  • Apache-2.0

🏷️ Available Versions

Tag Size (+ 0.2 GB projector) BPW Notes
Q4_K_M 0.54 GB 4.85 Recommended
Q5_K_M 0.59 GB 5.68 Higher quality
Q6_K 0.65 GB 6.56 Very high quality
latest / Q8_0 0.83 GB 8.5 Recommended

💻 Quick Start

ollama run richardyoung/xiaomi-ocr-0
# then drag an image file into the prompt, or send it in the API "images" field

🛠️ Use Cases

  • Whole-page document parsing to Markdown
  • Receipts and forms to JSON (KIE)
  • Questions about the text in an image

✅ Verified

Tested through Ollama before upload (Q4_K_M and Q8_0) on a synthetic invoice with the prompt Extract the text in the image.; Q4_K_M returned: ‘INVOICE 4471 / Date: 2026-09-28 / Widgets x3 … \(42.00 / TOTAL: \)86.20’.

🔧 Technical Details

  • Base Model: SeerRay-Lab/Xiaomi-OCR-0
  • Parameters: 0.8B
  • Context Length: 256K tokens
  • Quantization: GGUF via llama.cpp with an importance matrix (calibration_datav3); vision projector at F16
  • License: Apache-2.0 (inherited from the base model)

🙏 Acknowledgments

  • Base Model: SeerRay Lab (Xiaomi)
  • Quantization: llama.cpp

Built & maintained by Richard Young · DeepNeuro