selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

openbmb logo

MiniCPM-OCR-1.0

openbmb·Instruct·released 21 Oct 2026

Apache 2.01.3B256K ctx ≈3.4 GB
Your GPU
ollama run hf.co/mradermacher/MiniCPM-OCR-1.0-GGUF:Q4_K_M
All 4 runners ↓

MiniCPM-OCR-1.0 is an instruct-tuned OCR and document AI model from openbmb with 1.3B parameters. It takes image and text inputs and returns text, with a context length of 262,144 tokens. It is released under the Apache 2.0 licence, which allows commercial use, and it works with English and Chinese. The model has no other sizes in its family listed on this page.

How much VRAM does MiniCPM-OCR-1.0 need?

At FP16 / BF16 MiniCPM-OCR-1.0 needs about 3.4 GB of GPU memory.

--vram
any
--gpus
--quant
QuantisationWeightsTotal
4-bitRecommended default for local use0.5 GB file≈1.1 GB
8-bitLossless in practice, twice the size of Q40.8 GB file≈1.4 GB
FP16 / BF16recommendedFull precision, as released1.4 GB file≈2.2 GB

Estimates for the weights plus runtime overhead; activations vary with resolution and batch size. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.

Can the RTX 4060 run MiniCPM-OCR-1.0? →

Run MiniCPM-OCR-1.0 locally

--quantQ4_K_Mdefault; pick your GPU to tailor itmradermacher/MiniCPM-OCR-1.0-GGUF

Q4_K_M straight from Hugging Facedocs
ollama run hf.co/mradermacher/MiniCPM-OCR-1.0-GGUF:Q4_K_M

Install Ollama

OpenAI-compatible server with a web UIdocs
llama-server -hf mradermacher/MiniCPM-OCR-1.0-GGUF:Q4_K_M

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

Install llama.cpp

Download with the lms CLIdocs
lms get mradermacher/MiniCPM-OCR-1.0-GGUF@Q4_K_M

Then load it from the LM Studio app or with `lms load`.

Install LM Studio

Serve an OpenAI-compatible APIdocs
vllm serve openbmb/MiniCPM-OCR-1.0
Smaller AWQ builddocs
vllm serve openbmb/MiniCPM-OCR-1.0-AWQ
Docker Compose (NVIDIA)docs
yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: openbmb/MiniCPM-OCR-1.0
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 8000.

Install vLLM

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFQ2_K0.4 GB767
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFQ3_K_S0.4 GB767
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFQ3_K_M0.5 GB767
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFQ3_K_L0.5 GB767
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFIQ4_XS0.5 GB767
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFQ4_K_S0.5 GB767
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFQ4_K_M0.5 GB767
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFQ5_K_S0.6 GB767
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFQ5_K_M0.6 GB767
mradermacher/MiniCPM-OCR-1.0-GGUFGGUFQ6_K0.6 GB767

About 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. • 🏆 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.

Full model card on Hugging Face →

Alternatives to MiniCPM-OCR-1.0

All alternatives →
zai-org logo

GLM-OCR

zai-org·OCR

≈3.5 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.

1.3B128K ctx MIT
1.9MJan 2026ollama
tencent logo

HunyuanOCR

tencent·OCR

≈3.0 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).

1.1B128K ctx Tencent Hunyuan Community License
617.7KNov 2025gguf
lightonai logo

LightOnOCR-2-1B

lightonai·OCR

≈2.8 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.

1B16K ctx Apache 2.0
726.3KJan 2026gguf
ATH-MaaS logo

OvisOCR3

ATH-MaaS·OCR

≈2.4 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.

853M256K ctx Apache 2.0
375.6KOct 2026gguf
XingChen-AGI logo

TeleOCR

XingChen-AGI·OCR

≈3.7 GB

TeleOCR is a lightweight (~1.2B parameters), open-source Vision-Language Model designed specifically for document parsing.

1.4B125K ctx Apache 2.0
18.7KAug 2026gguf
opendatalab logo

MinerU2.5-Pro-2605-1.2B

opendatalab·OCR

≈3.1 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:

1.2B8K ctx Apache 2.0
35.2KMay 2026gguf

MiniCPM-OCR-1.0 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.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.