Instructions to use VillanovaAI/Villanova-2B-VL-2603-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VillanovaAI/Villanova-2B-VL-2603-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="VillanovaAI/Villanova-2B-VL-2603-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("VillanovaAI/Villanova-2B-VL-2603-GGUF", dtype="auto")

llama-cpp-python

How to use VillanovaAI/Villanova-2B-VL-2603-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="VillanovaAI/Villanova-2B-VL-2603-GGUF",
	filename="Villanova-2B-VL-2603-BF16.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use VillanovaAI/Villanova-2B-VL-2603-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 VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16

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 VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16

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 VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16

Use Docker

docker model run hf.co/VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16

LM Studio
Jan

vLLM

How to use VillanovaAI/Villanova-2B-VL-2603-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VillanovaAI/Villanova-2B-VL-2603-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": "VillanovaAI/Villanova-2B-VL-2603-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/VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16

SGLang

How to use VillanovaAI/Villanova-2B-VL-2603-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "VillanovaAI/Villanova-2B-VL-2603-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VillanovaAI/Villanova-2B-VL-2603-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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "VillanovaAI/Villanova-2B-VL-2603-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VillanovaAI/Villanova-2B-VL-2603-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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use VillanovaAI/Villanova-2B-VL-2603-GGUF with Ollama:
```
ollama run hf.co/VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16
```

Unsloth Studio

How to use VillanovaAI/Villanova-2B-VL-2603-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 VillanovaAI/Villanova-2B-VL-2603-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 VillanovaAI/Villanova-2B-VL-2603-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VillanovaAI/Villanova-2B-VL-2603-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use VillanovaAI/Villanova-2B-VL-2603-GGUF with Docker Model Runner:
```
docker model run hf.co/VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16
```

Lemonade

How to use VillanovaAI/Villanova-2B-VL-2603-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VillanovaAI/Villanova-2B-VL-2603-GGUF:BF16

Run and chat with the model

lemonade run user.Villanova-2B-VL-2603-GGUF-BF16

List all available models

lemonade list

Model Card for Villanova-2B-VL-2603-GGUF

Villanova-2B-VL-2603 is a fully open, multilingual Vision-Language Model developed by Villanova.AI. Part of the Villanova project, it extends our text-only Villanova-2B-2603 to visual understanding while preserving native support for five European languages. All model weights, training data sources, and training details are publicly released.

This repo contains GGUF format model files for the VillanovaAI/Villanova-2B-VL-2603 model.

Model Family

Villanova-2B-Base-2603 — Base model (4.4T)
↳ Villanova-2B-2603 — SFT / Instruct
↳ Villanova-2B-2603-GGUF — Quantized
↳ Villanova-2B-VL-2603 — Vision-Language Instruct
↳ Villanova-2B-VL-2603-GGUF — Quantized — 📍 This model

Villanova-2B-Base-2512-Preview — Base model (2.2T) (previous version, not recommended)
↳ Villanova-2B-2512-Preview — SFT / Instruct (previous version, not recommended)

About GGUF

GGUF is a format introduced by llama.cpp.

It is a file format for storing and distributing LLMs that is designed for portability and efficient inference on the edge.

Quick Usage with llama.cpp

You can run this model directly using the llama-cli tool (part of llama.cpp).

To run the model with the Q8_0 quantization directly from Hugging Face:

llama-cli -hf VillanovaAI/Villanova-2B-VL-2603-GGUF:Q8_0

Downloads last month: 40

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

Model tree for VillanovaAI/Villanova-2B-VL-2603-GGUF

Base model

VillanovaAI/Villanova-2B-Base-2603

Quantized

(3)

this model

Collection including VillanovaAI/Villanova-2B-VL-2603-GGUF

Villanova 2603

Collection

Collection of all models in the Villanova 2603 family. • 7 items • Updated Apr 23 • 4