Ollama · deepseek-ocr

<img src="/assets/library/deepseek-v3/069ccc94-63b0-41e6-b2b3-e8e56068ab1a" width="320" /> > DeepSeek-OCR requires [Ollama v0.13.0](https://github.com/ollama/ollama/releases) or later. DeepSeek-OCR i…

ollama/deepseek-ocr

<img src="/assets/library/deepseek-v3/069ccc94-63b0-41e6-b2b3-e8e56068ab1a" width="320" />

> DeepSeek-OCR requires [Ollama v0.13.0](https://github.com/ollama/ollama/releases) or later.

DeepSeek-OCR is a vision-language model that can perform token-efficient optical character recognition (OCR).

![fig1.png](/assets/library/deepseek-ocr/e93c9353-3836-4680-a7f1-148ad3e47eff)

### Example inputs

Please note, the model is sensitive to its input. For example, a missing punctuation or new line may cause an improper output.

``` ollama run deepseek-ocr "/path/to/image\n<|grounding|>Given the layout of the image." ```

``` ollama run deepseek-ocr "/path/to/image\nFree OCR." ```

``` ollama run deepseek-ocr "/path/to/image\nParse the figure." ```

``` ollama run deepseek-ocr "/path/to/image\nExtract the text in the image." ```

``` ollama run deepseek-ocr "/path/to/image\n<|grounding|>Convert the document to markdown." ```

### Examples

![show1.jpg](/assets/library/deepseek-ocr/445a87aa-b34e-4a85-8aba-921dd54cfd86)

![show2.jpg](/assets/library/deepseek-ocr/78c11fd6-d1be-4983-a08a-5188c65fcd1f)

![show3.jpg](/assets/library/deepseek-ocr/44b2ac4a-d52e-4f77-843d-3c828e7ecaf0)

![show4.jpg](/assets/library/deepseek-ocr/39e4d41b-634e-407a-a26e-7880c0a2b137)

### References

- [Arxiv paper](https://arxiv.org/abs/2510.18234)

Specifications & capabilities

Published model ID
deepseek-ocr

Deployments & artifacts

1–3 / 3

ollama

source id
ollama
execution mode
local
parameter size
3.3B
parameter count
3300000000
parameter count is approximate
true
quantization level
F16
context window
8000
context window is approximate
true
artifact size bytes
6687239934
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.3B
parameter count
3300000000
parameter count is approximate
true
quantization level
F16
context window
8000
context window is approximate
true
artifact size bytes
6687239934
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.3B
parameter count
3300000000
parameter count is approximate
true
quantization level
F16
context window
8000
context window is approximate
true
artifact size bytes
6687239934
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace