Modem AI vs ArcanAI

Modem AI is a private assistant for iPhone, iPad, and Mac. It runs a language model on your device, so your conversations stay there. There is no account, and your prompts stay on the device rather than going to a cloud chatbot. The first launch downloads Phi-3-mini, about 2.7 GB. After that, you can chat without a connection. Replies can take longer than a cloud service. That is the trade for keeping the conversation on the device. The model needs about 4 GB of available memory. What you can do • Chat in natural language, including answers with lists and code • Dictate a message with on-device speech recognition. Audio stays on the device • Write a system message, and set temperature, top-p, and maximum response length • Choose light, dark, or system appearance • Copy a reply, start over, or clear history Privacy Your prompts and replies stay on the device. Modem AI does not read them. If you send feedback or report a reply, only what you choose to submit is shared. The app may send anonymous performance statistics, such as whether a feature succeeded. Those statistics do not include your conversations.

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.