Agent Mag
SUBSCRIBE
Deepseek OCR
All models
DeepSeekDeepSeekDeepSeekLocal runtimeFree

Deepseek OCR

8K contextOllama install3 tags

Deepseek OCR is available through Ollama for local agent workflows, with support for text, image input. DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.

What is Deepseek OCR?

Deepseek OCR is a local model entry from Ollama that Agent Mag tracks for install commands, available tags, modalities, and agent workflow fit. Builders can install it with the Agent Mag CLI and run it through Ollama on their own machine.

Agent Mag install
Ollama model ID

DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.

Modalities
Input
textimage
Output
text
Ollama Tags
TagSizeContextInput
deepseek-ocr:latest6.7GB8Ktext, image
deepseek-ocr:3b6.7GB8Ktext, image

Related local models

Deepseek V4 Flash
LocalOllama

DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.

Deepseek V3.2
LocalOllama

DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.

Deepseek V3.1
671bOllama

DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.

Deepseek R1
1.5b, 7bOllama

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

Related content

Browse the AI models directory

Compare pricing, local installs, context windows, and modality filters across the full model catalog.

Explore AI agent tools

Find frameworks, SDKs, and infrastructure tools that pair with this model in production workflows.

Read Agent Mag model and agent articles

See Agent Mag coverage of model benchmarks, agent frameworks, and deployment patterns.