Instructions to use RKNNAI/RK182X-LLM-MiniCPM5-2B 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-LLM-MiniCPM5-2B 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-LLM-MiniCPM5-2B
# Run inference directly in the terminal:
llama cli -hf RKNNAI/RK182X-LLM-MiniCPM5-2B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RKNNAI/RK182X-LLM-MiniCPM5-2B
# Run inference directly in the terminal:
llama cli -hf RKNNAI/RK182X-LLM-MiniCPM5-2B

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf RKNNAI/RK182X-LLM-MiniCPM5-2B
# Run inference directly in the terminal:
./build/bin/llama cli -hf RKNNAI/RK182X-LLM-MiniCPM5-2B

Use Docker

docker model run hf.co/RKNNAI/RK182X-LLM-MiniCPM5-2B

Llama new
LM Studio
Jan

vLLM

How to use RKNNAI/RK182X-LLM-MiniCPM5-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RKNNAI/RK182X-LLM-MiniCPM5-2B"
# 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-LLM-MiniCPM5-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RKNNAI/RK182X-LLM-MiniCPM5-2B

Ollama
How to use RKNNAI/RK182X-LLM-MiniCPM5-2B with Ollama:
```
ollama run hf.co/RKNNAI/RK182X-LLM-MiniCPM5-2B
```
Unsloth Desktop

How to use RKNNAI/RK182X-LLM-MiniCPM5-2B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RKNNAI/RK182X-LLM-MiniCPM5-2B

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RKNNAI/RK182X-LLM-MiniCPM5-2B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RKNNAI/RK182X-LLM-MiniCPM5-2B with Docker Model Runner:
```
docker model run hf.co/RKNNAI/RK182X-LLM-MiniCPM5-2B
```

Lemonade

How to use RKNNAI/RK182X-LLM-MiniCPM5-2B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RKNNAI/RK182X-LLM-MiniCPM5-2B

Run and chat with the model

lemonade run user.RK182X-LLM-MiniCPM5-2B-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use RKNNAI/RK182X-LLM-MiniCPM5-2B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RKNNAI/RK182X-LLM-MiniCPM5-2B

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default RKNNAI/RK182X-LLM-MiniCPM5-2B

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RKNNAI/RK182X-LLM-MiniCPM5-2B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RKNNAI/RK182X-LLM-MiniCPM5-2B

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "RKNNAI/RK182X-LLM-MiniCPM5-2B" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

RK182X-LLM-MiniCPM5-2B

English | 简体中文

1. Model Overview

This repository provides an RKNN LLM model converted from openbmb/MiniCPM5-2B.

Model ID: RKNNAI/RK182X-LLM-MiniCPM5-2B
Model Display Name: RK182X-LLM-MiniCPM5-2B
RKNN Runtime Version: v1.1.0
Source Model: openbmb/MiniCPM5-2B
Model Type: LLM
Chip Label: RK182X
Supported Chips: RK1820, RK1828

Available Models

RKNN Runtime Version	Configuration Directory	Supported Chips	Quantization	NPU Cores	Context Length (tokens)	KVCache
`v1.1.0`	MiniCPM5-2B-w4a16-8-13312-kv-int4	RK1820, RK1828	w4a16	8	13312 (13k)	int4
`v1.1.0`	MiniCPM5-2B-w4a16-8-18432-normal	RK1828	w4a16	8	18432 (18k)	fp16
`v1.1.0`	MiniCPM5-2B-w4a16-8-48128-kv-int4	RK1828	w4a16	8	48128 (47k)	int4
`v1.1.0`	MiniCPM5-2B-w4a16-8-5632	RK1820, RK1828	w4a16	8	5632 (5.5k)	fp16
`v1.1.0`	MiniCPM5-2B-w8a16-8-14336-normal	RK1828	w8a16	8	14336 (14k)	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-LLM-MiniCPM5-2B --revision v1.1.0 --local_dir ./RK182X-LLM-MiniCPM5-2B

Download the full repository from Hugging Face:

hf download RKNNAI/RK182X-LLM-MiniCPM5-2B --revision v1.1.0 --local-dir ./RK182X-LLM-MiniCPM5-2B

Download a specific configuration from ModelScope:

from modelscope import snapshot_download

snapshot_download(
    "RKNNAI/RK182X-LLM-MiniCPM5-2B",
    revision="v1.1.0",
    allow_patterns=["README.md", "README_CN.md", "LICENSE", "Notice", "MiniCPM5-2B-w4a16-8-13312-kv-int4/**"],
    local_dir="./RK182X-LLM-MiniCPM5-2B",
)

Download a specific configuration from Hugging Face:

hf download RKNNAI/RK182X-LLM-MiniCPM5-2B --revision v1.1.0 --include "README.md" "README_CN.md" "LICENSE" "Notice" "MiniCPM5-2B-w4a16-8-13312-kv-int4/**" --local-dir ./RK182X-LLM-MiniCPM5-2B

4. SHA-256 Verification

Run in the configuration directory:

cd ./RK182X-LLM-MiniCPM5-2B/MiniCPM5-2B-w4a16-8-13312-kv-int4
sha256sum -c SHA256SUMS

Deploy only after all entries show OK.

5. Compatibility and Limitations

See the Available Models table for the chips supported by each configuration.
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.

6. Copyright and License

See LICENSE in the repository root for the source model license; The RKNN Toolkit and RKNN Runtime license terms also apply.

This release is an RKNN-converted/quantized derivative of the source model. The original license and attribution notices are retained; see Notice.

Downloads last month: 119

GGUF

Model size

0 params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for RKNNAI/RK182X-LLM-MiniCPM5-2B

Base model

openbmb/MiniCPM5-2B

Quantized

(128)

this model