Instructions to use RKNNAI/RK182X-OCR-PaddleOCR-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RKNNAI/RK182X-OCR-PaddleOCR-VL with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RKNNAI/RK182X-OCR-PaddleOCR-VL
# Run inference directly in the terminal:
llama cli -hf RKNNAI/RK182X-OCR-PaddleOCR-VL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RKNNAI/RK182X-OCR-PaddleOCR-VL
# Run inference directly in the terminal:
llama cli -hf RKNNAI/RK182X-OCR-PaddleOCR-VL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RKNNAI/RK182X-OCR-PaddleOCR-VL
# Run inference directly in the terminal:
./llama-cli -hf RKNNAI/RK182X-OCR-PaddleOCR-VL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RKNNAI/RK182X-OCR-PaddleOCR-VL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RKNNAI/RK182X-OCR-PaddleOCR-VL

Use Docker

docker model run hf.co/RKNNAI/RK182X-OCR-PaddleOCR-VL

LM Studio
Jan

vLLM

How to use RKNNAI/RK182X-OCR-PaddleOCR-VL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RKNNAI/RK182X-OCR-PaddleOCR-VL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RKNNAI/RK182X-OCR-PaddleOCR-VL",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RKNNAI/RK182X-OCR-PaddleOCR-VL

Ollama
How to use RKNNAI/RK182X-OCR-PaddleOCR-VL with Ollama:
```
ollama run hf.co/RKNNAI/RK182X-OCR-PaddleOCR-VL
```
Unsloth Desktop
Docker Model Runner
How to use RKNNAI/RK182X-OCR-PaddleOCR-VL with Docker Model Runner:
```
docker model run hf.co/RKNNAI/RK182X-OCR-PaddleOCR-VL
```

Lemonade

How to use RKNNAI/RK182X-OCR-PaddleOCR-VL with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RKNNAI/RK182X-OCR-PaddleOCR-VL

Run and chat with the model

lemonade run user.RK182X-OCR-PaddleOCR-VL-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

RK182X-OCR-PaddleOCR-VL

English | 简体中文

1. Model Overview

This repository provides an RKNN OCR model converted from PaddlePaddle/PaddleOCR-VL.

Model ID: RKNNAI/RK182X-OCR-PaddleOCR-VL
Model Display Name: RK182X-OCR-PaddleOCR-VL
RKNN Runtime Version: v1.1.0
Source Model: PaddlePaddle/PaddleOCR-VL
Model Type: OCR
Chip Label: RK182X
Supported Chips: RK1820, RK1828

Available Models

RKNN Runtime Version	Configuration Directory	Supported Chips	Resolution	Quantization	NPU Cores	Context Length (tokens)	KVCache
`v1.1.0`	PaddleOCR-VL-504x504-w4a16-8-4096-normal	RK1820, RK1828	Vision: 504x504	Vision: w4a16; LLM: w4a16; Vision MLP-AR: w4a16	Vision: 8; LLM: 8; Vision MLP-AR: 8	LLM: 4096 (4k)	LLM: fp16

2. Files

File or Directory	Description
`LICENSE`	Source model license
`Notice`	License, usage requirements, and attribution
`<configuration-directory>/`	Matching model files
Subdirectory `README.md`	Configuration documentation (English)
Subdirectory `README_CN.md`	Configuration documentation (Chinese)
Subdirectory `config.json`	Model configuration and file manifest
Subdirectory `SHA256SUMS`	SHA-256 checksums of the files in this directory (excluding this file)

3. Download

Download the full repository from ModelScope:

modelscope download --model RKNNAI/RK182X-OCR-PaddleOCR-VL --revision v1.1.0 --local_dir ./RK182X-OCR-PaddleOCR-VL

Download the full repository from Hugging Face:

hf download RKNNAI/RK182X-OCR-PaddleOCR-VL --revision v1.1.0 --local-dir ./RK182X-OCR-PaddleOCR-VL

Download a specific configuration from ModelScope:

from modelscope import snapshot_download

snapshot_download(
    "RKNNAI/RK182X-OCR-PaddleOCR-VL",
    revision="v1.1.0",
    allow_patterns=["README.md", "README_CN.md", "LICENSE", "Notice", "PaddleOCR-VL-504x504-w4a16-8-4096-normal/**"],
    local_dir="./RK182X-OCR-PaddleOCR-VL",
)

Download a specific configuration from Hugging Face:

hf download RKNNAI/RK182X-OCR-PaddleOCR-VL --revision v1.1.0 --include "README.md" "README_CN.md" "LICENSE" "Notice" "PaddleOCR-VL-504x504-w4a16-8-4096-normal/**" --local-dir ./RK182X-OCR-PaddleOCR-VL

4. SHA-256 Verification

Run in the configuration directory:

cd ./RK182X-OCR-PaddleOCR-VL/PaddleOCR-VL-504x504-w4a16-8-4096-normal
sha256sum -c SHA256SUMS

Deploy only after all entries show OK.

5. Compatibility and Limitations

Supported Chips: RK1820, RK1828.
Use the matching RKNN Runtime and driver. Check the device-side version with rknn-smi -v before running.
Use the files from the selected configuration directory together.