Instructions to use rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-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 rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-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 rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL

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 rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL

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 rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL

Ollama
How to use rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF with Ollama:
```
ollama run hf.co/rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL
```
Unsloth Desktop
Docker Model Runner
How to use rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF with Docker Model Runner:
```
docker model run hf.co/rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL
```

Lemonade

How to use rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rodrigomt/WEBGEN-4B-Preview-480B-Double-Distill-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.WEBGEN-4B-Preview-480B-Double-Distill-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Atomic Chat

🧠 WEBGEN-4B-Preview-480B-Double-Distill GGUFs

Quantized version of: BasedBase/WEBGEN-4B-Preview-480B-Double-Distill-FP32

📦 Available GGUFs

Format	Description
F16	Full precision (16-bit), better quality, larger size ⚖️
Q8_K_XL	Quantized (8-bit XL variant, based on the quantization table of the unsloth model Qwen3-4B-Thinking-2507), smaller size, faster inference ⚡
Q4_K_XL	Quantized (4-bit XL variant, based on the quantization table of the unsloth model Qwen3-4B-Thinking-2507), smaller size, faster inference ⚡

🚀 Usage

Example with llama.cpp:

./main -m ./gguf-file-name.gguf -p "Hello world!"

Downloads last month: 11

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

16-bit