DeepSeek AI · deepseekocr

Can I run deepseek-ocr?

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

Family maximum: 8K contextimagetextMIT License1 builds

Parameter counts and memory belong to each build below. A family can contain several sizes and tasks; fitting in memory is not a quality ranking.

Calculate memory for a build and context

Check it against my PC

deepseek-ocr system requirements

Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.

Download size and memory required for each deepseek-ocr build
Build	Quantization	Download	Memory needed
deepseek-ocr:3b3B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13	F16	6.2 GB	~7.4 GB

Showing the 1 smallest non-alias builds. Choose any build and change the context. A context above the build's documented maximum is a hypothetical calculation, not a supported setting.

How to run deepseek-ocr locally

1.Install Ollama for Windows, macOS or Linux.
2.Download this exact build in a terminal: ollama pull deepseek-ocr:3b
3.Check the source for the build's task. For text generation, run ollama run deepseek-ocr:3b. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.

Frequently asked questions about deepseek-ocr

How much VRAM do I need to run deepseek-ocr?: At 4K context, the smallest published build of deepseek-ocr (F16) needs roughly 7.4 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
Can I run deepseek-ocr without a dedicated GPU?: A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 7.4 GB at 4K context, plus headroom for your operating system. Check the build's runtime requirements. We have not measured its speed on your CPU.
How big is the deepseek-ocr download?: The smallest published build is 6.2 GB. Leave some extra free disk space beyond the download itself.
How do I run deepseek-ocr locally?: Install Ollama, then download a specific build with "ollama pull deepseek-ocr:3b". For a build that supports text generation, use ollama run with the same tag. Check the model source for its task and prompt format.

Will deepseek-ocr run on your PC?

Scan your hardware once and get a verdict for this model and every build — free, no account.

Check my PC

Compare with similar models

deepseek-llm deepseek-r1 deepseek-coder deepseek-coder-v2 deepseek-v2 deepseek-v2.5 deepseek-v3 deepseek-v3.1

Or start from your memory: 8 GB VRAM, 12 GB VRAM, 16 GB VRAM, 24 GB VRAM or a 16 GB Mac.

Model data from the official Ollama registry · verified 13/10/2026