DeepSeek-OCR-2

TitanML/DeepSeek-OCR-2

Image Text to Text3.4B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
20.4K
Total downloads
23.5K
Gained 7D
Gained 30D
Likes
0
Rank · tracked models
#5,547
this week
Parameters
3.4B
Last source update
Aug 21, 2026

Downloads over time

Rolling recent-window downloads as reported

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Likes over time

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Overview

DeepSeek-OCR-2 is a image text to text model published by TitanML. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 4h ago.

Published
Apr 6, 2026
Last updated
Aug 21, 2026
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
3,389,119,360
Spaces
Derivative models
Velocity 7D/day
transformerssafetensorsdeepseek_vl_v2feature-extractiondeepseekvision-languageocrcustom_codeimage-text-to-textconversationalmultilingualarxiv:2601.20552

Similar models

Models similar to DeepSeek-OCR-2
ModelDL 30D
DeepSeek-OCR-2deepseek-ai1.3M
DeepSeek-OCR-2deepseek-community11.8K
DeepSeek-OCR-2unsloth2,514
DeepSeek-OCR-2-GPTQ-INT8bartsolutions1,231
Universal-DeepSeek-OCR-2Dogacel930
DeepSeek-OCR-2-bf16mlx-community629