# MiniCPM-OCR-1.0

> MiniCPM-OCR 1.0 (1.3B) is the first OCR-specific model in the MiniCPM-V/o family. It focuses on text-centric document understanding — text, tables, formulas, charts, seals, and structured information extraction — and balances quality against speed on real-world captures.

- **Organisation:** openbmb
- **Category:** OCR & Document AI, Vision-Language Models
- **Parameters:** 1.3B
- **Context length:** 262,144 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-10-21
- **Hugging Face:** 280.7K downloads (30 days), 447 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q4_K_M | 1.38 |
| Q8_0 | 2.04 |
| F16 | 3.41 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [LM Studio](https://lmstudio.ai)
- [vLLM](https://selfhost.directory/project/vllm)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

MiniCPM-OCR 1.0 (1.3B) is the first OCR-specific model in the MiniCPM-V/o family. It focuses on text-centric document understanding — text, tables, formulas, charts, seals, and structured information extraction — and balances quality against speed on real-world captures.

• 🏆 SOTA document parsing: 93.68 on Real5-OmniDocBench, a benchmark for real-world
• document parsing, with leading results on OmniDocBench v1.6, Wild-OmniDocBench, and
• olmOCR-Bench. Handles Chinese and English documents and PDFs, including scans, curved pages,
• photographs, skewed pages, and recaptured documents.
• ⚡ Efficient inference. With DSpark decoding acceleration
• (BF16, GGUF) end-to-end
• processing efficiency improves by 55%. Throughput is about 1.49× PaddleOCR-VL-1.6 and
• 3.62× MinerU2.5 Pro.
• 🔍 General recognition and information extraction: 54.7 on OCRBench v2, plus key
• information extraction (KIE) for downstream automation.
• 🛠️ Easy to deploy and develop: vLLM, SGLang, llama.cpp, and Ollama from day one, with
• quantized variants and multi-chip builds. Supports further fine-tuning, and ships a pip SDK,
• a full API, and agent workflows. Online demos: China ·
• Global.

Among the open-source OCR models compared, MiniCPM-OCR 1.0 reaches 1.2 pages/s and the highest equal-weight average score across OmniDocBench v1.6, Real5-OmniDocBench, Wild-OmniDocBench, and olmOCR-Bench.

## Alternatives

- [zai-org/GLM-OCR](https://selfhost.directory/models/zai-org/glm-ocr) (1.3B, MIT, ≈3.46 GB): GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization.
- [tencent/HunyuanOCR](https://selfhost.directory/models/tencent/hunyuanocr) (1.1B, Tencent Hunyuan Community License, ≈3 GB): 📦 Model layout. This repository hosts HunyuanOCR-1.5 checkpoint at the root (target base weights). The DFlash speculative-decoding draft lives under dflash/, and the previous HunyuanOCR-1.0 is archived under v1.0/ (load it with subfolder="v1.0", or download the v1.0/ directory directly).
- [ATH-MaaS/OvisOCR3](https://selfhost.directory/models/ath-maas/ovisocr3) (853M, Apache 2.0, ≈2.41 GB): OvisOCR3 is a unified 0.8B multimodal model for OCR and document understanding. It integrates document parsing, general OCR, key information extraction, document figure captioning, and cross-page table reconstruction into a single compact model.
- [lightonai/LightOnOCR-2-1B](https://selfhost.directory/models/lightonai/lightonocr-2-1b) (1B, Apache 2.0, ≈2.75 GB): Best OCR model . LightOnOCR-2-1B is LightOn's flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks.
- [XingChen-AGI/TeleOCR](https://selfhost.directory/models/xingchen-agi/teleocr) (1.4B, Apache 2.0, ≈3.66 GB): TeleOCR is a lightweight (~1.2B parameters), open-source Vision-Language Model designed specifically for document parsing.
- [opendatalab/MinerU2.5-Pro-2605-1.2B](https://selfhost.directory/models/opendatalab/mineru2.5-pro-2605-1.2b) (1.2B, Apache 2.0, ≈3.08 GB): MinerU2.5-Pro is our latest document parsing model (PDF-to-Markdown) that establishes a new industry standard. By focusing entirely on data engineering without altering the original 1.2B-parameter architecture, it delivers exceptional results across the board:

More: https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/alternatives

## Runs well on

- [GeForce RTX 4060](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/rtx-4060): F16
- [Apple M4 (16 GB)](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/apple-m4-16gb): F16
- [Radeon RX 6700 XT](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/rx-6700-xt): F16
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/rtx-3060): F16
- [Arc B580](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/arc-b580): F16
- [Tesla T4](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/tesla-t4): F16

## Similar size

- [zai-org/GLM-OCR](https://selfhost.directory/models/zai-org/glm-ocr) (1.3B)
- [tencent/HunyuanOCR](https://selfhost.directory/models/tencent/hunyuanocr) (1.1B)
- [PaddlePaddle/PaddleOCR-VL-1.6](https://selfhost.directory/models/paddlepaddle/paddleocr-vl-1.6) (959M)
- [lightonai/LightOnOCR-2-1B](https://selfhost.directory/models/lightonai/lightonocr-2-1b) (1B)
- [PaddlePaddle/PaddleOCR-VL](https://selfhost.directory/models/paddlepaddle/paddleocr-vl) (959M)
- [XingChen-AGI/TeleOCR](https://selfhost.directory/models/xingchen-agi/teleocr) (1.4B)

## FAQ

**How much VRAM does MiniCPM-OCR-1.0 need?**
About 3.4 GB at FP16 / BF16.

**Can MiniCPM-OCR-1.0 run on the RTX 4060?**
Yes. It fits at FP16 / BF16 (about 2.2 GB). It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.

**Can I use MiniCPM-OCR-1.0 commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**How do I run MiniCPM-OCR-1.0 with Ollama or llama.cpp?**
With Ollama: ollama run hf.co/mradermacher/MiniCPM-OCR-1.0-GGUF:Q4_K_M. With llama.cpp: llama-server -hf mradermacher/MiniCPM-OCR-1.0-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/openbmb/MiniCPM-OCR-1.0
- github: https://github.com/OpenBMB/MiniCPM-OCR
- demo: https://platform.modelbest.ai/console/playground/document-parse

---
Source: https://selfhost.directory/models/openbmb/minicpm-ocr-1.0