Built-in Models of PrivateAI:
- Gemma 2 (Default): Google's lightweight, state-of-the-art model for various text generation tasks
- Llama 3.2: Advanced model for diverse language tasks
- Phi-3.5 mini: Microsoft's lightweight model with strong reasoning capabilities
- Orca mini: General-purpose model suitable for entry-level hardware
- Rocket 3B: Compact model with outstanding performance in benchmarks
- Mistral: High-performance open-source model
- NeuralBeagle: Cutting-edge model excelling in instruction following and reasoning
- OpenHermes: Versatile assistant with improved code generation capabilities
- WizardLM: Advanced language model with broad capabilities, trained without alignment constraints
- Silicon Maid: Specialized model for creative and role-playing tasks
- Gemma 2 (Default): Google's lightweight, state-of-the-art model for various text generation tasks
- Llama 3.2: Advanced model for diverse language tasks
- Phi-3.5 mini: Microsoft's lightweight model with strong reasoning capabilities
- Orca mini: General-purpose model suitable for entry-level hardware
- Rocket 3B: Compact model with outstanding performance in benchmarks
- Mistral: High-performance open-source model
- NeuralBeagle: Cutting-edge model excelling in instruction following and reasoning
- OpenHermes: Versatile assistant with improved code generation capabilities
- WizardLM: Advanced language model with broad capabilities, trained without alignment constraints
- Silicon Maid: Specialized model for creative and role-playing tasks
Premium Feature:
Model Flexibility: Add any compatible GGUF model file to tailor the AI experience to your specific needs
Unlock the full potential of AI while maintaining complete control over your data. Whether you're a privacy enthusiast, a tech professional, or simply curious about AI, our app offers a secure and powerful on-device AI experience.
Note: Uncensored models have no guardrails. Users are responsible for any content generated or actions taken with the models.
Shout out to the open source AI/ML community for their invaluable contributions!
Model Flexibility: Add any compatible GGUF model file to tailor the AI experience to your specific needs
Unlock the full potential of AI while maintaining complete control over your data. Whether you're a privacy enthusiast, a tech professional, or simply curious about AI, our app offers a secure and powerful on-device AI experience.
Note: Uncensored models have no guardrails. Users are responsible for any content generated or actions taken with the models.
Shout out to the open source AI/ML community for their invaluable contributions!
Features of PocketPal AI :
Offline AI Assistance: Run language models directly on your device without internet connectivity.
Model Flexibility: Download and swap between multiple SLMs, including Danube 2 and 3, Phi, Gemma 2, and Qwen.
Auto Offload/Load: Automatically manage memory by offloading models when the app is in the background.
Inference Settings: Customize model parameters like system prompt, temperature, BOS token, and chat templates.
Real-Time Performance Metrics: View tokens per second and milliseconds per token during AI response generation
Offline AI Assistance: Run language models directly on your device without internet connectivity.
Model Flexibility: Download and swap between multiple SLMs, including Danube 2 and 3, Phi, Gemma 2, and Qwen.
Auto Offload/Load: Automatically manage memory by offloading models when the app is in the background.
Inference Settings: Customize model parameters like system prompt, temperature, BOS token, and chat templates.
Real-Time Performance Metrics: View tokens per second and milliseconds per token during AI response generation