ArcanAI vs Clutcha

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.

Clutcha AI— a smart assistant that runs entirely on your iPhone. Inference happens on-device, your conversations never leave the device, and there is no account and no data collection. • On-device inference: chat with no network connection (the network is only used to download models) • Upgraded to the latest MLX inference engine — steadier long conversations, more accurate multi-turn memory, more reliable tool calls • A lightweight model is built in and ready to use; download 4B / 7B / 9B models for more capability (7 in total) • 11 device tools: calculator, date & time, files, system, battery, translate, Safari, clipboard, reminders, location, contacts • Web search (new): optional and off by default, with Tavily and Wikipedia — source links can be opened to verify • Full LaTeX math and Markdown rendering: headings, lists, tables, quotes, code blocks. Turn rendering off to read the raw text • Longer answers, less often cut short: higher output limits, a clear notice when a reply hits the limit, and one-tap continuation • Settings and info commands open a panel: /help /status /model /set /prompt /language /tools /kb /game /downloader • Adjustable session settings: context window, temperature, thinking budget, memory ceiling — remembered per model, so switching models keeps each model's own settings • Sampling tuned to each model's official recommendations (Qwen3 / Qwen3.5 / Qwen2.5 / DeepSeek-R1) • Knowledge base Q&A, plus Gomoku and chess with AI review • Privacy first: no data collection, no tracking — your data stays on your device. Only if you turn on web search and run the tool is your query sent to the provider you choose • Requirements: tested on iPhone 15 Pro Max (8GB); 12GB and up leaves more headroom for large models • Pro unlocks: 4B / 7B / 9B models, Chess Coach, parameter tuning, custom prompts and web search