Lumey vs Local LLM

Lumey runs LLMs entirely on your iPhone. No servers. No logs. No telemetry. Chats, voice notes, and documents you import never leave the device. Pick from open-weight and proprietary models, side by side. A quick reasoner for everyday questions, a heavier model for code or long-form work; simply switch between them in a tap. Every model runs locally on Apple Silicon. Bring your own knowledge. Attach PDFs, plain text, or markdown directly to a chat. Lumey chunks and embeds the content on-device, so retrieval happens locally. Install curated knowledge packs for specific domains, or mention them mid-chat to scope a single reply. Organise your data into multiple vaults. Keep work and personal context separate. Turn on Travel Mode and every vault locks behind Face ID the moment the app backgrounds. WHAT'S INSIDE • Open-weight and proprietary LLMs running locally on Apple Silicon • Curated knowledge packs that plug into on-device retrieval • Manage multiple vaults to compartmentalize chats, documents, and voice notes • Voice notes transcribed entirely on-device • Travel Mode: biometric lock on backgrounding and vault hiding LUMEY PRO Unlock every model and every knowledge pack with a monthly or yearly subscription. The free tier includes the proprietary system model and some starter packs, enough to use Lumey as a private daily assistant without paying. Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

Local LLM runs language models on your iPhone. No account is required. Chat, ask about photos, work with documents and use live voice. With Canvas, build websites, interactive pages and games from a conversation, then preview and edit them in the app. Features depend on the selected model. Download models from the catalog, or use Apple’s on-device model on supported devices when available. Core AI models require iOS 27 or later. Other supported models remain available on older systems. Inference and conversation history stay on your device. Model downloads, the catalog and model artwork use the network. Optional Web Search sends a query derived from your message to Tavily and may read result websites. Weather requests use Apple geocoding and WeatherKit for the requested city, without requesting device location. Voice input prefers on-device recognition. If it is unavailable or fails, Apple’s online speech service may process audio when network speech recognition is enabled. You can disable this in Privacy settings. Requires iOS 17 or later. Model availability depends on your device, OS, memory and storage. Downloads require internet; supported offline chat works after setup. Models can make mistakes. Do not rely on replies for medical, legal or financial decisions.