Instructions to use Miguelms13/Wiguel-AI-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Miguelms13/Wiguel-AI-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Miguelms13/Wiguel-AI-GGUF",
	filename="Wiguel-AI.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Miguelms13/Wiguel-AI-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 Miguelms13/Wiguel-AI-GGUF
# Run inference directly in the terminal:
llama cli -hf Miguelms13/Wiguel-AI-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Miguelms13/Wiguel-AI-GGUF
# Run inference directly in the terminal:
llama cli -hf Miguelms13/Wiguel-AI-GGUF

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 Miguelms13/Wiguel-AI-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Miguelms13/Wiguel-AI-GGUF

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 Miguelms13/Wiguel-AI-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Miguelms13/Wiguel-AI-GGUF

Use Docker

docker model run hf.co/Miguelms13/Wiguel-AI-GGUF

LM Studio
Jan

vLLM

How to use Miguelms13/Wiguel-AI-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Miguelms13/Wiguel-AI-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": "Miguelms13/Wiguel-AI-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Miguelms13/Wiguel-AI-GGUF

Ollama
How to use Miguelms13/Wiguel-AI-GGUF with Ollama:
```
ollama run hf.co/Miguelms13/Wiguel-AI-GGUF
```

Unsloth Studio

How to use Miguelms13/Wiguel-AI-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 Miguelms13/Wiguel-AI-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 Miguelms13/Wiguel-AI-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Miguelms13/Wiguel-AI-GGUF to start chatting

How to use Miguelms13/Wiguel-AI-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Miguelms13/Wiguel-AI-GGUF

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": "Miguelms13/Wiguel-AI-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Miguelms13/Wiguel-AI-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 Miguelms13/Wiguel-AI-GGUF

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 Miguelms13/Wiguel-AI-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Miguelms13/Wiguel-AI-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Miguelms13/Wiguel-AI-GGUF

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 "Miguelms13/Wiguel-AI-GGUF" \
  --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 Miguelms13/Wiguel-AI-GGUF with Docker Model Runner:
```
docker model run hf.co/Miguelms13/Wiguel-AI-GGUF
```

Lemonade

How to use Miguelms13/Wiguel-AI-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Miguelms13/Wiguel-AI-GGUF

Run and chat with the model

lemonade run user.Wiguel-AI-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Model Card for Wiguel-AI Core Engine

This Model Card details the integration, features, and usage of the main artificial intelligence model used in the Wiguel-AI application, supported by an intelligent local execution and offline fallback system.

Model Details

The Wiguel-AI engine is a highly efficient and low-latency conversational model. It is highly optimized for local processing directly on the user's device, ensuring excellent performance and maximum privacy.

In this implementation, it works as follows:

Local Mode (In-Browser/WebGPU): Executes artificial intelligence processing and weights storage via WebWorker and WebGPU directly on your machine. Everything happens within the browser without sending any data to the cloud or central servers.
Hybrid/Bridge Mode: By using the local connection script, the system can expand its capabilities to interact locally, manage model downloads, and ensure absolute and uninterrupted availability of your AI assistant.

AI URL

You can access the application at the following link: https://wiguel-ai.vercel.app/

How It Works

This model is used as the conversational brain of Wiguel-AI to:

Answer direct queries quickly.
Serve as an interactive assistant through a Progressive Web App (PWA) web interface.
Process natural language keeping all context private and secure.
Operate offline once the necessary files have been temporarily stored or cached.

The ecosystem encapsulates this model in asynchronous workflows and real-time streams, allowing fluent text generation.

1. Wiguel-AI

How to use: Wiguel-AI is designed to be a personal assistant that runs directly in your browser or through a local bridge for greater system access. To use the AI functionality, the interface connects seamlessly and downloads the resources needed to operate. All computation is optimized so as not to depend on large data centers when using offline mode.

Bridge Link (Wiguel Bridge): For advanced capabilities and local environment control, Wiguel-AI uses a bridge script. This bridge allows the application to securely communicate with local resources, handle background downloads, and provide offline inference without complications.

You can download the synchronization script from here: wiguel-bridge.py (GitHub)

Once downloaded, place it in your working folder and run it in your terminal:

python wiguel-bridge.py

The bridge script will start a local server that will automatically communicate with the Wiguel-AI web interface. Furthermore, when necessary, the bridge automatically downloads the model to your machine in the background, allows you to chat offline, and at the end of the session when closing the process, it performs an automatic cleanup to delete temporary files and the downloaded model from your hard drive.

Downloads last month: -

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants