Instructions to use Abiray/Youtu-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 Abiray/Youtu-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 Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/Youtu-VL-4B-Instruct-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 Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/Youtu-VL-4B-Instruct-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 Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Abiray/Youtu-VL-4B-Instruct-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 Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Abiray/Youtu-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 "Abiray/Youtu-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": "Abiray/Youtu-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/Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M

Ollama
How to use Abiray/Youtu-VL-4B-Instruct-GGUF with Ollama:
```
ollama run hf.co/Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Abiray/Youtu-VL-4B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use Abiray/Youtu-VL-4B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abiray/Youtu-VL-4B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Youtu-VL-4B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Youtu-VL-4B-Instruct-GGUF

This repository contains GGUF format model files for Tencent's Youtu-VL-4B-Instruct.

These files are compatible with llama.cpp, LM Studio, and other tools that support GGUF.

⚠️ CRITICAL: How to Use (Vision Capabilities)

This is a Vision-Language Model. To use its "eyes" (image recognition), you MUST load two files:

The Model: A quantized file (e.g., Youtu-VL-4B-Instruct-Q4_K_M.gguf)
The Vision Projector: The file named mmproj-Youtu-VL-4b-Instruct-BF16.gguf (included in this repo).

🚀 Usage Instructions

1. llama.cpp (CLI)

You must use the --mmproj flag to point to the vision file.

./llama-cli -m Youtu-VL-4B-Instruct-Q4_K_M.gguf \
  --mmproj mmproj-Youtu-VL-4b-Instruct-BF16.gguf \
  --image your_image.jpg \
  -p "Describe this image detailedly." \
  -n 512 \
  --temp 0.1

Downloads last month: 136

GGUF

Model size

5B params

Architecture

deepseek2

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for Abiray/Youtu-VL-4B-Instruct-GGUF

Base model

tencent/Youtu-VL-4B-Instruct

Quantized

(4)

this model