OCR models / rednote (dots)

dots.mocr

Name: dots.mocr
Author: rednote (dots)

rednote (dots) · released 2026-03-19 · data checked 2026-11-06

dots.mocr is a 3B-parameter OCR and document-parsing model from rednote (dots) (CN), released 2026-03-19 under the MIT license. It scores 83.9 on olmOCR-Bench (#7 of 24). It needs about 7.1 GB of memory at 16-bit.

Successor to dots.ocr, first released as dots.ocr-1.5; also converts charts and diagrams to SVG code. Reports OmniDocBench v1.5 sub-scores but no overall score.

OmniDocBench v1.6

—

Not reported

olmOCR-Bench

83.9

#7 of 24 models

Parameters

OCR specialist

Memory to run

~7.1 GB

16-bit weights plus about 1 GB

Benchmarks

olmOCR-Bench Lab-reported83.9

Best: OXR 1.0 87.8

The tick marks the best score on each benchmark. See how to read the ranking.

Specifications

Lab: rednote (dots) (CN)
Type: OCR / document parsing specialist
Total parameters: 3B
License: MIT
Memory to run: ~7.1 GB at 16-bit
Released: 2026-03-19

Weights and usage on Hugging Face ↗

Closest alternatives

jina-ocr-v1 (3.4B, 83.4 on olmOCR-Bench, CC-BY-NC-4.0)
LightOnOCR-3 1B (1B, 84.5 on olmOCR-Bench, Apache-2.0)
LightOnOCR-2 1B (1B, 83.2 on olmOCR-Bench, Apache-2.0)
MiniCPM-OCR 1.0 (1.3B, 82.7 on olmOCR-Bench, Apache-2.0)

Sources

https://huggingface.co/dots-studio/dots.mocr

Something wrong here? Report it.