DeepSeek-OCR 2
DeepSeek-OCR 2 is an AI model published by DeepSeek-AI, released on 2026-01-28, for Multimodal model, with 3.5B parameters, and 32K tokens context length, requiring about 7GB storage, under the DEEPSEEK LICENSE AGREEMENT license.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
DeepSeek-OCR 2 is an AI model published by DeepSeek-AI, released on 2026-01-28, for Multimodal model, with 3.5B parameters, and 32K tokens context length, requiring about 7GB storage, under the DEEPSEEK LICENSE AGREEMENT license.
Follow DataLearner on WeChat for AI model updates and research notes.
No curated comparisons for this model yet.
Want a custom combination? Open the compare tool
