LightOnOCR-3-0.8B-GGUF
LightOnOCR-3-0.8B, developed by lightonai, is the lightest and most efficient model in the LightOnOCR-3 family, designed for end-to-end Optical Character Recognition (OCR) and comprehensive document understanding. Built on the Qwen3.5 vision-language architecture, it streamlines complex document pipelines into a single model featuring two primary modes: a default transcription mode that outputs full-page Markdown text, and a "grounding" mode that returns bounding box coordinates and semantic labels for every visual element. Beyond standard text extraction, the model provides advanced visual understanding by automatically describing images and converting charts into structured HTML data tables. Capable of processing diverse formats—including tables, receipts, forms, multi-column layouts, and math notation—LightOnOCR-3-0.8B offers a fast, versatile, and Apache 2.0-licensed solution for both commercial and research document processing tasks.
- Speculative Decoding — No
Model Files
| File Name | Quant Type | File Size | File Link | Description |
|---|---|---|---|---|
| LightOnOCR-3-0.8B.BF16.gguf | BF16 | 1.52 GB | Link | Full BF16 weights. Highest quality, largest file size. |
| LightOnOCR-3-0.8B.Q3_K_L.gguf | Q3_K_L | 491 MB | Link | Lower quality but usable, good for low RAM availability. |
| LightOnOCR-3-0.8B.Q3_K_M.gguf | Q3_K_M | 466 MB | Link | Low quality. |
| LightOnOCR-3-0.8B.Q4_K_M.gguf | Q4_K_M | 529 MB | Link | Good quality, default size for most use cases, recommended. |
| LightOnOCR-3-0.8B.Q4_K_S.gguf | Q4_K_S | 505 MB | Link | Slightly lower quality with more space savings, recommended. |
| LightOnOCR-3-0.8B.Q5_K_M.gguf | Q5_K_M | 578 MB | Link | High quality, recommended. |
| LightOnOCR-3-0.8B.Q5_K_S.gguf | Q5_K_S | 564 MB | Link | High quality, recommended. |
| LightOnOCR-3-0.8B.Q6_K.gguf | Q6_K | 630 MB | Link | Very high quality, near perfect, recommended. |
| LightOnOCR-3-0.8B.Q8_0.gguf | Q8_0 | 812 MB | Link | Extremely high quality, generally unneeded but max available quant. |
| LightOnOCR-3-0.8B.mmproj-bf16.gguf | mmproj-bf16 | 207 MB | Link | Multimodal projection file in BF16 format. Used for vision/language models. |
| LightOnOCR-3-0.8B.mmproj-q8_0.gguf | mmproj-q8_0 | 116 MB | Link | Multimodal projection file in Q8_0 quantization. Smaller size for vision capabilities. |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp