Instructions to use Renesas/Qwen3-VL-4B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Renesas/Qwen3-VL-4B-Instruct-GGUF 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 Renesas/Qwen3-VL-4B-Instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Renesas/Qwen3-VL-4B-Instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

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 Renesas/Qwen3-VL-4B-Instruct-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

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 Renesas/Qwen3-VL-4B-Instruct-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

Use Docker

docker model run hf.co/Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

LM Studio
Jan

vLLM

How to use Renesas/Qwen3-VL-4B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Renesas/Qwen3-VL-4B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Renesas/Qwen3-VL-4B-Instruct-GGUF",
		"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/Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

Ollama
How to use Renesas/Qwen3-VL-4B-Instruct-GGUF with Ollama:
```
ollama run hf.co/Renesas/Qwen3-VL-4B-Instruct-GGUF:F16
```

Unsloth Studio

How to use Renesas/Qwen3-VL-4B-Instruct-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Renesas/Qwen3-VL-4B-Instruct-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Renesas/Qwen3-VL-4B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Renesas/Qwen3-VL-4B-Instruct-GGUF to start chatting

How to use Renesas/Qwen3-VL-4B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Renesas/Qwen3-VL-4B-Instruct-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Renesas/Qwen3-VL-4B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

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 Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Renesas/Qwen3-VL-4B-Instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

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 "Renesas/Qwen3-VL-4B-Instruct-GGUF:F16" \
  --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"

Docker Model Runner
How to use Renesas/Qwen3-VL-4B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/Renesas/Qwen3-VL-4B-Instruct-GGUF:F16
```

Lemonade

How to use Renesas/Qwen3-VL-4B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Renesas/Qwen3-VL-4B-Instruct-GGUF:F16

Run and chat with the model

lemonade run user.Qwen3-VL-4B-Instruct-GGUF-F16

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Qwen3-VL-4B-Instruct - Renesas X5H

Introduction

This repository contains Qwen3-VL-4B-Instruct model, optimized for Renesas X5H platform for Image inference.

Model Architecture: Qwen3‑4B‑VL is a lightweight decoder‑only multimodal Transformer that jointly processes visual and textual inputs in an auto‑regressive framework using an integrated vision encoder and efficient attention mechanisms.
Source Model: Qwen3-VL-4B-Instruct

Performance

The following performance metrics were measured with a prompt.

Type	Model	Precision	Device	Offloading	Response Rate (tokens/sec)
Mixed offloading (alpha)	Qwen3-VL-4B-Instruct	FP16	X5H - Single Cluster NPX	VisionTower CPU(fp16) + Language Decoder (fp16)	6.29 tokens/sec
Mixed offloading (alpha)	Qwen3-VL-4B-Instruct	W4A16	X5H - Single Cluster NPX	VisionTower CPU(fp16) + Language Decoder (w4a16)	11.48 tokens/sec

Prerequisites

To run model, you need:

Renesas X5H Board
Runner installer
Hugging Face CLI: For downloading the model.

Deployment

The two released modes for deployment.

alpha mode offers mixed offloading where Vision tower, projector and merger runs on CPU and Language decoder on NPX.

Qwen3-VL-4B-Instruct (W4A16, Mixed_Offloading)

Download the installer qwen3-4b-vl-w4a16-runner-0.1.0-Linux.sh from Files and version tab under w4a16\binaries\rcar-x5hv1\xOS_v4.32 folder.

Copy the installer to the X5H board and run the installer.

bash ./qwen3-4b-vl-w4a16-runner-0.1.0-Linux.sh --prefix=./ --exclude-subdir --skip-license

Download the model files - Qwen3-VL-4B-Instruct-fp16.gguf and mmproj-Qwen3VL-4B-Instruct-F16.gguf from Files and version tab under fp16 folder and copy to the installed directory on the X5H board.

Expected directory structure on the X5H board.

 qwen3-4b-vl-w4a16-runner
 ├── Qwen3-VL-4B-Instruct-fp16.gguf
 ├── firmwares
 ├── kernel_modules
 ├── mmproj-Qwen3VL-4B-Instruct-F16.gguf
 ├── qwen3-4b-vl-w4a16-runner
 ├── qwen3-4b-w4a16
 ├── scripts
 ├── setup_npu.sh
 └── test_img

Qwen3-VL-4B-Instruct (FP16, Mixed_Offloading)

Download the installer qwen3-4b-vl-fp16-runner-0.1.0-Linux.sh from Files and version tab under fp16\binaries\rcar-x5hv1\xOS_v4.32 folder.

Copy the installer to the X5H board and run the installer.

bash ./qwen3-4b-vl-fp16-runner-0.1.0-Linux.sh --prefix=./ --exclude-subdir --skip-license

Download the model files - Qwen3-VL-4B-Instruct-fp16.gguf and mmproj-Qwen3VL-4B-Instruct-F16.gguf from Files and version tab under fp16 folder and copy to the installed directory on the X5H board.

Expected directory structure on the X5H board.

 qwen3-4b-vl-fp16-runner
 ├── Qwen3-VL-4B-Instruct-fp16.gguf
 ├── firmwares
 ├── kernel_modules
 ├── mmproj-Qwen3VL-4B-Instruct-F16.gguf
 ├── qwen3-4b-vl-fp16-runner
 ├── scripts
 ├── setup_npu.sh
 └── test_img

Inference

Qwen3-VL-4B-Instruct (W4A16, Mixed_Offloading)

bash ./setup_npu.sh
./qwen3-4b-vl-w4a16-runner -i <image file name>

Qwen3-VL-4B-Instruct (FP16, Mixed_Offloading)

bash ./setup_npu.sh
./qwen3-4b-vl-fp16-runner -i <image file name>

Downloads last month: 2

GGUF

Model size

4B params

Architecture

qwen3vl

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Renesas/Qwen3-VL-4B-Instruct-GGUF

Base model

Qwen/Qwen3-VL-4B-Instruct

Quantized

(97)

this model

Collections including Renesas/Qwen3-VL-4B-Instruct-GGUF

GGUF

Collection

7 items • Updated 9 days ago

X5H Hardware - NPU

Collection

10 items • Updated 9 days ago