Instructions to use RKNNAI/RK182X-VLM-Janus-Pro-1B 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-VLM-Janus-Pro-1B 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-VLM-Janus-Pro-1B
# Run inference directly in the terminal:
llama cli -hf RKNNAI/RK182X-VLM-Janus-Pro-1B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RKNNAI/RK182X-VLM-Janus-Pro-1B
# Run inference directly in the terminal:
llama cli -hf RKNNAI/RK182X-VLM-Janus-Pro-1B

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-VLM-Janus-Pro-1B
# Run inference directly in the terminal:
./llama-cli -hf RKNNAI/RK182X-VLM-Janus-Pro-1B

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-VLM-Janus-Pro-1B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RKNNAI/RK182X-VLM-Janus-Pro-1B

Use Docker

docker model run hf.co/RKNNAI/RK182X-VLM-Janus-Pro-1B

LM Studio
Jan

vLLM

How to use RKNNAI/RK182X-VLM-Janus-Pro-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RKNNAI/RK182X-VLM-Janus-Pro-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RKNNAI/RK182X-VLM-Janus-Pro-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RKNNAI/RK182X-VLM-Janus-Pro-1B

Ollama
How to use RKNNAI/RK182X-VLM-Janus-Pro-1B with Ollama:
```
ollama run hf.co/RKNNAI/RK182X-VLM-Janus-Pro-1B
```
Unsloth Desktop
Docker Model Runner
How to use RKNNAI/RK182X-VLM-Janus-Pro-1B with Docker Model Runner:
```
docker model run hf.co/RKNNAI/RK182X-VLM-Janus-Pro-1B
```

Lemonade

How to use RKNNAI/RK182X-VLM-Janus-Pro-1B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RKNNAI/RK182X-VLM-Janus-Pro-1B

Run and chat with the model

lemonade run user.RK182X-VLM-Janus-Pro-1B-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

RK182X-VLM-Janus-Pro-1B

English | 简体中文

1. Model Overview

This repository provides an RKNN model converted from deepseek-ai/Janus-Pro-1B.

Model ID: RKNNAI/RK182X-VLM-Janus-Pro-1B
Model Display Name: RK182X-VLM-Janus-Pro-1B
RKNN Runtime Version: v1.1.0
Source Model: deepseek-ai/Janus-Pro-1B
Model Type: VLM
Chip Label: RK182X
Supported Chips: RK1828

Available Models

RKNN Runtime Version	Configuration Directory	Supported Chips	Resolution	Quantization	NPU Cores	Context Length (tokens)	KVCache
`v1.1.0`	Janus-Pro-1B-384x384-w4a16-8-15872	RK1828	Vision: 384x384	Vision: w4a16; LLM: w4a16	Vision: 8; LLM: 8	LLM: 15872 (15.5k)	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-VLM-Janus-Pro-1B --revision v1.1.0 --local_dir ./RK182X-VLM-Janus-Pro-1B

Download the full repository from Hugging Face:

hf download RKNNAI/RK182X-VLM-Janus-Pro-1B --revision v1.1.0 --local-dir ./RK182X-VLM-Janus-Pro-1B

Download a specific configuration from ModelScope:

from modelscope import snapshot_download

snapshot_download(
    "RKNNAI/RK182X-VLM-Janus-Pro-1B",
    revision="v1.1.0",
    allow_patterns=["README.md", "README_CN.md", "LICENSE", "NOTICE", "Janus-Pro-1B-384x384-w4a16-8-15872/**"],
    local_dir="./RK182X-VLM-Janus-Pro-1B",
)

Download a specific configuration from Hugging Face:

hf download RKNNAI/RK182X-VLM-Janus-Pro-1B --revision v1.1.0 --include "README.md" "README_CN.md" "LICENSE" "NOTICE" "Janus-Pro-1B-384x384-w4a16-8-15872/**" --local-dir ./RK182X-VLM-Janus-Pro-1B

4. SHA-256 Verification

Run in the configuration directory:

cd ./RK182X-VLM-Janus-Pro-1B/Janus-Pro-1B-384x384-w4a16-8-15872
sha256sum -c SHA256SUMS

Deploy only after all entries show OK.

5. Compatibility and Limitations

Supported Chips: 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.
Provides image understanding and text generation; image generation components are not included.

6. Copyright and License

Source model license: DeepSeek Model License, See LICENSE for the full text and NOTICE for attribution and conversion modifications.
The artifacts in this repository are converted derivatives of the source weights, not unmodified upstream weights. They remain subject to the source model license and usage restrictions.
The applicable RKNN Toolkit and RKNN Runtime licenses also apply; runtime libraries are not included in this package.

Downloads last month: 139

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-VLM-Janus-Pro-1B

Base model

deepseek-ai/Janus-Pro-1B

Quantized

(6)

this model