My Local AI vs DeviceAI

My Local AI lets you ask questions, think through ideas, and write with AI on your iPhone or iPad. Run downloaded models on your device, use Apple Intelligence on supported devices, or connect to models running on your own Mac or PC. The guided setup helps you download a small AI model and choose whether to enable Memory, Calendar and Reminders. Downloaded models run locally with MLX. Switch models and manage their storage in the app. Use bigger models on your own computer. Add LM Studio, Ollama, llama.cpp, Unsloth or another compatible model server in Settings > Your computers. Choose which models appear in the chat's model menu. When you select one, the app sends the conversation to your chosen computer for a reply. If the computer is unavailable, the model on your iPhone or iPad can answer instead, and the chat tells you when it does. You can turn this fallback off. Have a spoken conversation in Voice Mode, with speech recognition and voice generation on your device. Download an available voice, then choose your voice and speaking speed in Settings. Bring an image or document into a chat and ask about it. Image understanding requires a compatible vision model. Create Word documents, Excel workbooks, PowerPoint presentations, and drawings from your requests. Save details you want the assistant to remember, choose a persona that stays with each chat, and read replies with Markdown and code formatting. Chats are stored on your device by default. If you want them on your other devices, you can turn on iCloud Sync. Web search and weather are separate, optional tools. Calendar and Reminders are also optional; actions that change your calendar or create reminders require your approval. You do not need a My Local AI account. Downloads require an internet connection and sufficient storage. Downloaded AI and voice models run on your device; optional online tools require internet access. Connecting to your computer requires a compatible model server and a reachable network address. On-device model availability depends on your device's memory. Made by Olanrewaju Oyinbooke.

Run powerful AI models entirely on your iPhone — no internet, no subscriptions, no data sharing. DeviceAI is a privacy-first chat app that runs large language models (LLMs) completely on your device using Apple's Metal GPU acceleration. Your conversations never leave your phone. KEY FEATURES • 100% On-Device Processing — All AI inference happens locally. Zero cloud dependency. • 60+ Open-Source Models — Choose from Llama, Qwen, Phi, Mistral, DeepSeek and more • Full Privacy — No data collection, no analytics, no telemetry. Your chats stay on your device. • Offline-First — Works perfectly without internet after model download • Streaming Responses — See AI responses appear in real-time • Reasoning Models — Support for advanced thinking models like DeepSeek R1 • Markdown & Code — Beautiful formatting with syntax highlighting • Customizable — Adjust system prompts, temperature, and generation parameters • Conversation History — All chats saved locally with Isar database PERFECT FOR • Privacy advocates who want AI without cloud exposure • Travelers and remote workers who need offline AI assistance • Developers testing open-source models • Students wanting unlimited, free AI tutoring • Anyone who values data sovereignty TECHNICAL DETAILS • Powered by llamadart (llama.cpp for Flutter) • Supports GGUF format models from HuggingFace • Metal GPU acceleration for fast inference (15-40 tokens/second) • Models range from 0.5B to 8B parameters • Requires iOS 16.0 or later Download models once, use forever. No subscriptions, no API keys, no compromises. Your data stays on your device. Always.