Instructions to use leeminwaan/qwen_3_4B_ViO_LR-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 leeminwaan/qwen_3_4B_ViO_LR-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 leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

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 leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

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 leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

Use Docker

docker model run hf.co/leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use leeminwaan/qwen_3_4B_ViO_LR-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leeminwaan/qwen_3_4B_ViO_LR-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": "leeminwaan/qwen_3_4B_ViO_LR-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

Ollama
How to use leeminwaan/qwen_3_4B_ViO_LR-GGUF with Ollama:
```
ollama run hf.co/leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M
```
Unsloth Desktop

How to use leeminwaan/qwen_3_4B_ViO_LR-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

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": "leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use leeminwaan/qwen_3_4B_ViO_LR-GGUF with Docker Model Runner:
```
docker model run hf.co/leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M
```

Lemonade

How to use leeminwaan/qwen_3_4B_ViO_LR-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.qwen_3_4B_ViO_LR-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use leeminwaan/qwen_3_4B_ViO_LR-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 leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

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 leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use leeminwaan/qwen_3_4B_ViO_LR-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M

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 "leeminwaan/qwen_3_4B_ViO_LR-GGUF:Q4_K_M" \
  --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"

🤖 Model Card for qwen_3_4B_ViO_LR-GGUF

This repo is packed with multiple quantized versions of leeminwaan/qwen_3_4B_ViO_LR in GGUF format. 🚀✨
Built for running efficiently on your everyday hardware - no need for enterprise-level specs to deploy these models. 💻🎯🔥

📋 Model Details

⚡ Quantization Results

Quantization	Size (vs. FP16)	Speed	Quality	Recommended For
Q2_K	Tiny 🐭	Lightning ⚡	Basic 📉	Quick prototypes, potato hardware 🧪
Q3_K_S	Mini 🐹	Super fast 🚀	Decent 📊	Mobile devices, quick tests 📱
Q3_K_M	Small 🐰	Fast 💨	Good 📈	Lightweight but better quality
Q3_K_L	Small+ 🐱	Fast ⚡	Good 📊	Speed with acceptable quality
Q4_0	Medium 🐺	Quick ⚡	Solid 👍	Daily driver, casual chats 💬
Q4_1	Medium 🦊	Quick 🚀	Solid+ 👌	Slight upgrade from Q4_0
Q4_K_S	Medium 🐻	Quick 💨	Nice ✨	Well-balanced choice ⚖️
Q4_K_M	Medium 🦁	Quick ⚡	Really nice 🌟	The crowd favorite 🏅
Q5_0	Chunky 🐘	Chill 🚶	Great 💪	Chatbots that actually make sense 🤖
Q5_1	Chunky 🦏	Chill ⏳	Great+ 🔥	When you need quality responses 💼
Q5_K_S	Big 🐳	Chill 🕐	Great+ ⭐	For the quality-conscious 🎯
Q5_K_M	Big 🦣	Chill ⌛	Excellent 🏆	High-end performance 💎
Q6_K	Massive 🐋	Slow 🐌	Near perfect 👑	Enthusiasts only
Q8_0	Absolute unit 🦕	Turtle 🐢	Basically perfect 💎	Max settings gang 🖥️

📝 Real talk:

Lower numbers = smaller files 📉, runs faster ⚡, but quality takes a hit 📊

Q4_K_M hits different - it's the sweet spot most people actually want 👥

Q6_K/Q8_0 are for perfectionists with beefy hardware 🏆🧙‍♂️

Everything here runs on regular consumer hardware 💻 - pick what matches your vibe! 🎯

📝 Model Description

Quantized by: leeminwaan 👨‍💻
Funded by [optional]: Solo project, no corporate backing 💰
Shared by [optional]: leeminwaan 🤝
Model type: Decoder-only transformer (the good stuff) 🧠🤖
Language(s) (NLP): Base on qwen_3_4B_ViO_LR
License: Apache-2.0 (free to use, modify, distribute) 📄⚖️

🔗 Model Sources

Repository: Hugging Face Repo 🤗📦
Quantization Tool: AllQuants 🔢⚡
Paper [optional]: No research paper (this is practical, not academic) 📝❌
Demo [optional]: Demo coming soon™ 🎮🔜

🚀 How to Get Started with the Model

# 🐍 Quick start - literally just this:
from huggingface_hub import hf_hub_download

# 📥 Grab the model (Q4_K_M is the sweet spot for most people)
model_path = hf_hub_download("leeminwaan/qwen_3_4B_ViO_LR-GGUF", "qwen_3_4B_ViO_LR-q4_k_m.gguf")
print("Downloaded:", model_path) # 🎊 You're good to go!

Available flavors: 🎁📦

Q2_K, Q3_K_S, Q3_K_M, Q3_K_L 🏃‍♂️💨 (Speed demons - perfect for testing)
Q4_0, Q4_1, Q4_K_S, Q4_K_M ⚖️✨ (The goldilocks zone - just right)
Q5_0, Q5_1, Q5_K_S, Q5_K_M 💪🎯 (For when you need that extra quality)
Q6_K, Q8_0 🏆👑 (Maxed out settings - if your hardware can handle it)

🎯 Training Details

📊 Training Data

This is a straight quantization - no extra training or fine-tuning involved. ✨

⚙️ Training Procedure

Took leeminwaan/qwen_3_4B_ViO_LR and compressed it into these GGUF formats. 🔄

🔧 Technical Specifications

💾 Software

llama.cpp for the heavy lifting 🦙
Python 3.10 + huggingface_hub for the workflow 🐍

📚 Citation

BibTeX: 📖🔬

@miscqwen_3_4B_ViO_LR-GGUF,
  title=qwen_3_4B_ViO_LR-GGUF Quantized Models},
  author={leeminwaan},
  year={2025}, % 🎊 Hot off the press!
  howpublished={\url{https://huggingface.co/leeminwaan/qwen_3_4B_ViO_LR-GGUF}}
}

APA: 📝✨

leeminwaan. (2025). qwen_3_4B_ViO_LR-GGUF Quantized Models [Computer software]. 💻 Hugging Face. https://huggingface.co/leeminwaan/qwen_3_4B_ViO_LR-GGUF 🤗

📖 Glossary

Quantization: Making models smaller by reducing number precision - trades some quality for efficiency. 🔢
GGUF: The file format that llama.cpp loves - optimized for fast inference. ⚡