Documentation

Complete guide to using AI Troll - your private, offline AI assistant.

Getting Started

First Launch

When you first open AI Troll, you'll see the onboarding screen where you will:

1. Learn about the app's capabilities

2. Review and accept the terms of use

3. Download your first AI model

Downloading Your First Model

1. Tap "Find Compatible Models" to browse available models

2. Filter by size, architecture, or quantization type

3. Select a model suitable for your device (smaller models use less memory)

4. Tap "Download" and wait for the download to complete

5. The model will be automatically activated once downloaded

Chat Screen

The main chat interface where you interact with your AI assistant.

• Start a Conversation: Simply type your message and tap send

• Clear Chat: Use the menu to clear the conversation history

• Model Info: Tap the model name to see details about the active model

Model Management

Access: Tap the models icon in the navigation bar

Sections:

• My Models: View imported and downloaded models

• Browse: Search HuggingFace for compatible models

Actions:

• Set Active: Choose which model to use for chat

• Delete: Remove downloaded models to free up storage

• Import: Add GGUF models from your device storage

Importing Local Models

AI Troll supports importing GGUF model files from your device:

1. Go to Model Management

2. Tap "Import Local Model"

3. Select a .gguf file from your device

4. The model will be added to your library

Note: GGUF format includes everything needed (model + tokenizer), so no additional files are required.

Settings

Generation Parameters:

• Temperature (0.1-2.0): Controls creativity. Lower = focused responses, Higher = creative/varied responses

• Top-K (1-100): Limits choices to the K most likely tokens

• Top-P (0.1-1.0): Nucleus sampling - considers tokens until cumulative probability reaches P

• Repetition Penalty (1.0-2.0): Reduces repetitive output

• Max Tokens: Maximum length of AI responses

Download Settings:

• WiFi Only: Restrict downloads to WiFi connections (recommended)

• Allow Metered: Allow downloads on mobile data

Model Compatibility

Supported Formats

AI Troll supports GGUF (GPT-Generated Unified Format) models. This modern format includes:

• The model weights

• Embedded tokenizer

• Model configuration

Quantization Types

Quantized models are optimized for mobile devices:

• Q4_K_M - Smallest size, Good quality, Low memory

• Q5_K_M - Small size, Better quality, Medium memory

• Q6_K - Medium size, Very Good quality, Medium-High memory

• Q8_0 - Large size, Excellent quality, High memory

Recommendation: Start with Q4_K_M or Q5_K_M for most devices.

Memory Requirements

• Check your device's available RAM before downloading large models

• The app will warn you if a model may be too large for your device

• Close other apps to free up memory for larger models

Tips & Best Practices

1. Start Small: Begin with smaller quantized models (1-3GB) to test your device's capabilities

2. Manage Storage: Delete unused models to free up space

3. WiFi Downloads: Use WiFi for downloading large models to avoid data charges

4. Battery: AI processing is CPU-intensive; plug in your device for extended sessions

5. Memory: Close background apps for better performance with larger models

Troubleshooting

Model won't load:

• Check if you have enough free RAM

• Try a smaller quantized version of the model

• Restart the app

Slow responses:

• Use a smaller/more quantized model

• Close background apps

• Ensure your device isn't overheating

Download fails:

• Check your internet connection

• Ensure you have enough storage space

• Try downloading a smaller model first