LightOnOCR-3-1B

LightOnOCR-3-1B: drop-in upgrade for LightOnOCR-2 with grounding, image descriptions and chart extraction.

🚀 Overview

GGUF build of lightonai/LightOnOCR-3-1B, the LightOnOCR-3 model that keeps the LightOnOCR-2-1B architecture, so switching requires no change, and adds grounding, image description and chart extraction. It ships with its vision projector, so image input works in Ollama.

Prompts: send the image with an empty prompt for plain transcription (Markdown), or with the prompt grounding to get every block with a label and a 0–1000 bounding box, image descriptions and chart data as tables. LightOn notes that other instructions are out of distribution. Recommended sampling: temperature 0.2, top_p 0.9 (set in the Ollama tags).

🎯 Key Features

• Drop-in upgrade for LightOnOCR-2-1B deployments
• Two modes: plain transcription, or grounding with labels and bounding boxes
• Handles tables, receipts, forms, charts, multi-column layouts, handwriting and math
• Apache-2.0: research and commercial use

🏷️ Available Versions

💻 Quick Start

ollama run richardyoung/lightonocr-3-1b
# then drag an image file into the prompt, or send it in the API "images" field

🛠️ Use Cases

• Upgrading existing LightOnOCR-2 pipelines
• Handwriting and form OCR
• Layout-aware extraction

✅ Verified

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

🔧 Technical Details

• Base Model: lightonai/LightOnOCR-3-1B
• Parameters: 0.6B
• Context Length: 16K 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: LightOn
• Quantization: llama.cpp

Built & maintained by Richard Young · DeepNeuro