Lighton · OCR
Lightonocr 3 0.8b
LightonOCRLightOnOCR familyOpen weights. One of its sources says the weights are publicly available.
LightOnOCR-3-0.8B is the smallest and fastest model in LightOn's open-weight LightOnOCR-3 family: an end-to-end OCR and document-understanding model (about 0.85B parameters, Qwen3.5 vision-language architecture) that converts documents into Markdown, with optional labelled bounding-box grounding, image descriptions and chart-to-table extraction.
Evidence and sources
Sources: Scaleway API data docs, Models.dev data, EURouter dataPrimary data from Scaleway API
from Models.dev: creator, family, variant, weights availability
from EURouter: description
Tags from its sources:open-sourceocrdocument-analysisvisionlightweight
Advantages and trade-offs
Compared with 10 representative OCR models
Advantages
Input & output
as stated by the model's providersText
Images
Files
Text
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works