Light AI vs Local Inference OnDevice Agent

Light AI is built to make conversations with AI more natural and helpful. It's a simple chat app that lets you talk with advanced AI models in a way that feels more natural. Light AI offers: • Conversation Threading - Keep your thoughts organized by branching conversations into different topics • Context Selection - Help the AI understand exactly what parts of your conversation are important • Voice Input - Sometimes it's easier to speak than type - Light AI can listen too • Simple Search - Find your past conversations without endless scrolling • Collapsible Messages - Keep your chat history tidy by expanding only what you need Light AI is an attempt to make AI interactions more intuitive. NOTE: Light AI requires a subscription to access all features. Monthly and yearly subscription options available. Terms: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

Your AI. Your phone. Nobody else's business. LocalInference runs powerful open AI models entirely on your device. Your conversations never leave your phone — no account, no cloud, no analytics, no tracking. Ever. PRIVATE BY ARCHITECTURE, NOT BY PROMISE • Everything runs on-device; works fully offline after a one-time model download • Zero data collection — we couldn't read your chats if we wanted to • API keys (optional) stored in the secure keychain, sent only to the provider you chose A REAL ASSISTANT, NOT JUST A CHATBOT • Tools: calculator, web search, date & time, webpage reading • Contacts & calendar integration — every write action asks you first • Ask about photos with vision models • Reads answers aloud with on-device voices BUILT FOR TINKERERS • 16 curated models from 0.5B to 8B — Qwen3, Llama, Gemma, DeepSeek R1, Phi, SmolVLM • Only models that fit your device's memory are offered • Live tok/s, time-to-first-token, and token counts per response • Thinking models show their reasoning in collapsible blocks • Bring your own keys: Anthropic, OpenAI, Google — or any OpenAI-compatible server (llama.cpp, LM Studio, Ollama) on your own network Built with Llama. Gemma models provided under the Gemma Terms of Use.