Lisor vs ArcanAI

XiaoWei Assistant captures notes and chats on your phone when you intentionally enable microphones and transcription. Exact features ship with each application update described in-product. MODELS AND STORAGE Inference runs locally when hardware allows. Delivered shards may download through Apple-hosted on-demand resources. Keep reliable network plus free disk until tags finish validating. Offline or unfinished downloads mean some AI workflows stay unavailable until then. DATA POSTURE Treat in-app disclosures and Privacy Policy online as authoritative. Designed for device-first journaling you control rather than unsolicited cloud LLM uploads. HOME LAN GATEWAY OPTIONAL Backing up to Mac requires your LAN, your gateway software, documented tokens and security you maintain. Nothing here bypasses lawful network boundaries. SCOPE LIMITS This is productivity tooling, not regulated medical advice, legal counsel or investment guidance. Outputs can be inaccurate with noise accents or chipset limits. Thank you for using XiaoWei Assistant.

ArcanAI is a private, on-device AI chat app that runs open-source language models entirely on your iPhone or iPad. No accounts. No subscriptions. No cloud. No internet required. Import any GGUF model from Hugging Face and start chatting — every conversation happens locally, powered by hardware-accelerated inference using Apple's Metal framework. Your messages never leave your device. KEY FEATURES - Run AI models 100% offline — on a plane, off the grid, anywhere - Import any GGUF model from Hugging Face — choose the size and capability that fits your device - Store and switch between up to 5 models at once - Analyze documents — upload PDFs, spreadsheets, text files, CSVs, and more - GPU-accelerated inference for fast, streaming responses - Full conversation history with multiple independent chats - Edit messages and regenerate responses - Customize temperature, max tokens, and system prompts - Beautiful dark UI with markdown-rendered responses - Text-to-speech support SUPPORTED MODEL FAMILIES Llama, Gemma, Mistral, Phi, Qwen, and any ChatML-compatible model. RECOMMENDED STARTER MODELS - Llama 3.2 1B (~570 MB) — great for older devices - Gemma 2 2B (~1.0 GB) — balanced performance - Qwen 2.5 3B (~1.5 GB) — multilingual and code capabilities PRIVACY FIRST Zero data collection. Zero telemetry. Zero crash reporting. Zero cloud sync. Your conversations and model files stay on your device — always.