Demo (CN / Global) · GitHub · Free API · Usage · DSpark · Skill

MiniCPM-OCR 1.0 DSpark — GGUF

GGUF build of the DSpark draft head for MiniCPM-OCR 1.0. A draft model, not a standalone OCR model — pair it with the matching main checkpoint.

Files

Use the main model's projector (mmproj-model-f16-4x.gguf from MiniCPM-OCR-1.0-gguf); this repository contains only the draft.

Parsing pipeline

MiniCPM-OCR 1.0 parses full documents as a two-stage pipeline orchestrated by the minicpm-ocr SDK. The two stages use separate models, run in separate environments, and may run on different machines:

• Stage 1 — Layout detection (SDK environment). The PP-DocLayoutV3 layout model detects document regions — text, tables, formulas, charts, seals — and determines reading order; the SDK crops each region. It runs locally inside the SDK environment and requires PaddlePaddle / PaddleX.
• Stage 2 — Region recognition (inference service). The SDK sends each cropped region over HTTP to a MiniCPM-OCR 1.0 inference service — served by vLLM, SGLang, llama.cpp, or Ollama — with a prompt matching the region type, then assembles the recognized content into the final Markdown / JSON in reading order.

See the model guide for more on architecture, parsing workflow, deployment options, and benchmark breakdowns.

Usage

llama-cli \
  -m MiniCPM-OCR-1_0-Q8_0.gguf \
  --mmproj mmproj-model-f16-4x.gguf \
  -md dspark-MiniCPM-OCR-1_0-Q8_0.gguf \
  --spec-type draft-dspark \
  --image page.png -p "Text Recognition:" \
  --jinja -ngl 99 -ngld 99 -fa on

-md is the draft model and --spec-type draft-dspark enables the draft; -ngld offloads draft layers to GPU.

llama-mtmd-cli does not accept a draft model. Use llama-cli or llama-server when enabling DSpark with multimodal input.

Each tier carries the absolute target token IDs in its d2t tensor (the safetensors export stores them delta-encoded).

Related checkpoints

FAQ

Installation, model downloads, GPU memory, input formats, and unexpected outputs: FAQ.

License

Model weights, code, and documentation are released under the Apache License 2.0.