All models

dots.ocr

byRedNoteRedNote· 30 Jul 2025
MultimodalSpecial purpose

RedNote (the Chinese version of Instagram) continues to release open models. RedNote is a somewhat surprising participant in the AI space, but goes to show how pervasive open model releases are in China. This Optical Character Recognition (OCR) model, building on top of Qwen3 1.7B, is not only relatively small (compared to other models in the 7-8B range), but it is also really good! There are multiple people independently reporting about its performance and being impressed by it. Also, check out this Twitter thread by William about his experience with fine-tuning the model.

Specs
Params1.7B
LicenseMIT
Tags
modelsmodels/llmsmodels/llms/multi-modalmultilingualartifacts/13curated/our-picks
Adoption · Interconnects
RAM score
Hugging Face Downloads
359K
last 30d
5.4M
all time
HF Likes
1.3K

Relative Adoption Metric contextualizes downloads against the model's size bucket.

VAIL
VAIL Fingerprint
0029:003b:004c:0074:00b0:0182:0401:5bb5

Explore other models with behavioral similarity to dots.ocr.

Related Models