Metadata-Version: 2.4
Name: ggufloader
Version: 2.0.0
Summary: Enhanced GGUF Model Loader with Advanced Resource Management - Local AI Chat Application
Author-email: Hussain Nazary <hussainnazary475@gmail.com>
Maintainer-email: Hussain Nazary <hussainnazary475@gmail.com>
License: MIT
Project-URL: Homepage, https://ggufloader.github.io
Project-URL: Documentation, https://ggufloader.github.io
Project-URL: Repository, https://github.com/GGUFloader/gguf-loader
Project-URL: Bug Tracker, https://github.com/GGUFloader/gguf-loader/issues
Project-URL: Changelog, https://github.com/GGUFloader/gguf-loader/releases
Project-URL: Website, https://ggufloader.github.io
Keywords: llama,gguf,ai,chat,local,assistant,resource-management,gpu-acceleration,llama-cpp,machine-learning,nlp,enhanced-ui
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: End Users/Desktop
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: MacOS
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Desktop Environment
Classifier: Topic :: Text Processing
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: llama-cpp-python>=0.2.72
Requires-Dist: PySide6>=6.6.1
Requires-Dist: psutil>=5.9.0
Requires-Dist: pywin32>=306; sys_platform == "win32"
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-qt>=4.0.0; extra == "dev"
Requires-Dist: black>=22.0.0; extra == "dev"
Requires-Dist: flake8>=4.0.0; extra == "dev"
Requires-Dist: mypy>=0.950; extra == "dev"
Dynamic: license-file

# GGUF Loader

**Advanced GGUF Model Loader with Enhanced Resource Management**

A powerful, user-friendly desktop application for loading and chatting with GGUF (GPT-Generated Unified Format) models locally. Features advanced hardware detection, resource optimization, and enhanced UI for the best local AI experience.

## 🚀 Key Features

### Enhanced Resource Management
- **Automatic Hardware Detection**: Detects GPU (RTX 4060, etc.), CPU cores, and RAM
- **Intelligent Resource Optimization**: Automatically configures optimal settings
- **GPU Acceleration Support**: Full CUDA support with memory management
- **Hardware-Aware Processing**: Shows detailed hardware info in processing mode

### Advanced UI Features
- **Enhanced Processing Display**: Shows hardware details like "GPU Accelerated (NVIDIA GeForce RTX 4060 - 8GB)"
- **Smart Progress Messages**: Detailed optimization information during model loading
- **Advanced Settings**: Persistent configuration with hardware validation
- **Clean, Professional Interface**: Optimized for productivity

### Core Functionality
- **Local AI Chat**: Complete privacy - no data sent to external servers
- **GGUF Model Support**: Load any GGUF format model locally
- **Streaming Responses**: Real-time AI responses with typing indicators
- **Conversation History**: Persistent chat history with export options
- **Cross-Platform**: Windows, macOS, and Linux support

## 📦 Installation

### New Installation
```bash
pip install ggufloader
```

### Upgrading from Previous Version
```bash
pip install --upgrade ggufloader
```

### Launch the Application
```bash
ggufloader
```

> **Note**: Version 2.0.0 includes major enhancements while maintaining full backward compatibility. Existing users can upgrade seamlessly to get all the new features.

## 🔧 Requirements

### System Requirements
- **Python**: 3.8 or higher
- **RAM**: 8GB minimum, 16GB+ recommended
- **GPU**: Optional but recommended (NVIDIA with CUDA support)
- **Storage**: 2GB+ free space for models

### Dependencies
- `llama-cpp-python>=0.2.72` - Core GGUF model loading
- `PySide6>=6.6.1` - Modern Qt-based UI
- `psutil>=5.9.0` - System resource monitoring
- `pywin32>=306` - Windows-specific features (Windows only)

## 🎯 Quick Start

1. **Install the package**:
   ```bash
   pip install ggufloader
   ```

2. **Launch the application**:
   ```bash
   ggufloader
   ```

3. **Load a GGUF model**:
   - Click "Browse" to select your GGUF model file
   - The app will automatically detect your hardware and optimize settings
   - Choose between CPU or GPU processing (if available)

4. **Start chatting**:
   - Type your message in the input field
   - Press Enter or click Send
   - Enjoy real-time AI responses!

## 🖥️ Hardware Optimization

### Automatic Configuration
The application automatically detects and configures:
- **GPU Memory**: Uses 80% of available VRAM for optimal performance
- **CPU Threads**: Uses 75% of available threads for efficient processing
- **Memory Management**: Intelligent memory allocation and cleanup

### Supported Hardware
- **NVIDIA GPUs**: RTX 4060, RTX 3080, RTX 4090, and more
- **AMD GPUs**: Basic support (CPU fallback recommended)
- **Intel CPUs**: Full optimization for all modern Intel processors
- **AMD CPUs**: Full optimization for Ryzen and other AMD processors

## ⚙️ Advanced Features

### Enhanced Processing Modes
- **GPU Accelerated**: Full GPU utilization with VRAM management
- **CPU Optimized**: Multi-threaded CPU processing with smart thread allocation
- **Hybrid Mode**: Automatic switching between GPU and CPU based on model size

### Settings Management
- **Hardware-Based Defaults**: Automatically configured for your system
- **Persistent Configuration**: Settings saved across application restarts
- **Advanced Tuning**: Fine-tune GPU memory, thread count, and more
- **Profile Management**: Save and load different configuration profiles

## 🛠️ Development

### For Developers
```bash
# Clone the repository
git clone https://github.com/GGUFloader/gguf-loader.git
cd gguf-loader

# Install in development mode
pip install -e .

# Install development dependencies
pip install -e .[dev]

# Run tests
pytest
```

## 📋 Changelog

### Version 2.0.0 - Major Enhanced Release
- ✅ **Enhanced Resource Management**: Automatic hardware detection with RTX 4060 optimization
- ✅ **Smart Floating Assistant**: AI-powered text processing addon
- ✅ **Advanced UI Features**: Resource monitoring with real-time system info
- ✅ **GPU Acceleration Support**: Full CUDA support with intelligent memory management
- ✅ **Advanced Settings**: Persistent configuration with hardware validation
- ✅ **Performance Optimizations**: Optimized resource utilization and memory management
- ✅ **Enhanced Processing Display**: Shows detailed hardware info during model loading
- ✅ **Comprehensive Error Handling**: Robust error recovery and user guidance

### Previous Versions
- ✅ Complete UI redesign with modern Qt interface
- ✅ GGUF model support with streaming responses
- ✅ Cross-platform compatibility
- ✅ Conversation history and export features

## 🤝 Contributing

We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.

## 📄 License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

## 🆘 Support

- **Website**: [https://ggufloader.github.io](https://ggufloader.github.io)
- **Issues**: [GitHub Issues](https://github.com/GGUFloader/gguf-loader/issues)
- **Documentation**: [Wiki](https://github.com/GGUFloader/gguf-loader/wiki)
- **Developer**: Hussain Nazary
- **Email**: hussainnazary475@gmail.com

## 🙏 Acknowledgments

- Built on top of [llama.cpp](https://github.com/ggerganov/llama.cpp)
- Uses [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) for Python bindings
- UI powered by [PySide6](https://doc.qt.io/qtforpython/)

---

**Experience the future of local AI with GGUF Loader Enhanced!** 🚀
