RUN THIS LLM

Search local LLM hardware requirements

← Back to all models

dots.ocr 3B

Rednote · 3B · Vision

Rednote's multilingual document parser that unifies layout detection and content recognition in one VLM: a 1.7B Qwen-style LLM plus a 1.2B vision encoder. SOTA on OmniDocBench for text, tables, and reading order; MIT license.

VRAM Requirements

QuantizationVRAM
Q4_K_M (smallest)1.8 GB
Q8_0 (balanced)3.3 GB
FP16 (full quality)6 GB

Specifications

Loading interactive analysis...

RTL
Add Run This LLM to your home screen
Get the Chrome Extension
Look up hardware requirements for any model right from your browser sidebar — no tab switching needed.
Add to Chrome — It's Free