---

base_model: dots-studio/dots.mocr

base_model_relation: quantized

license: mit

pipeline_tag: image-text-to-text

tags: [gguf, llama.cpp, ollama, vision, multimodal, ocr]

---

dots.mocr-GGUF

GGUF quantizations of dots-studio/dots.mocr with its vision projector, for llama.cpp and Ollama.

| File | What |

|---|---|

| dots.mocr-Q4_K_M.gguf | Language model, Q4_K_M (recommended) |

| dots.mocr-Q8_0.gguf | Language model, Q8_0 |

| mmproj-dots.mocr-F16.gguf | Vision projector (f16), required for images |

Ollama

ollama run richardyoung/dots.mocr

Tags: Q4_K_M (default, latest), Q8_0. Image input works in the CLI (drag in a file path) and via the API images field.

llama.cpp

llama-mtmd-cli -m dots.mocr-Q4_K_M.gguf --mmproj mmproj-dots.mocr-F16.gguf --image page.png -p "Transcribe all the text in this image."

Verified

Tested before upload through Ollama with a synthetic invoice and a shapes image (Q4_K_M shown):

• Invoice transcription: 'INVOICE 4471 / Date: 2026-09-28 / Widgets x3 ....... $42.00 / TOTAL: $86.20'
• Shapes: 'The image contains two shapes: a red circle and a blue square. The red circle is on the left side, and the blue square is on the right side. Both shapes are set'

Converted with llama.cpp convert_hf_to_gguf.py (text and --mmproj), quantized with llama-quantize.