SnapNote vs Gadeon

Turn photos into notes you can use. SnapNote organizes receipts, tables, meeting notes, study materials, and everyday documents into readable, editable, searchable notes. After downloading and activating a local model, text recognition, organization, and Ask Notes run on your device. No app account or cloud AI API is required. From photos to notes Capture pages with the camera or import images from your photo library. Review, crop, and rotate pages, then choose a document type or template. Keep the original images, OCR text, and organized result together so you can check and edit the output. Ask your own documents Select saved notes to summarize key points, compare information, or create action lists. Source references help you return to the relevant note and verify the answer. Preview, save, and share generated Markdown and CSV files within the app. Organize your way Manage your library with document types, tags, favorites, and search. Use built-in templates for common tasks, or define your own structure and instructions with custom templates. Export note results in multiple formats for further editing or archiving. Made for iPhone Duo Browse a list and its details side by side on the inner display. Split views cover Notes, Ask Notes, Generated Files, Templates, and Settings. The outer display and standard iPhones retain a comfortable single-column experience. On-device processing and privacy Photos, recognized text, and notes are processed and stored on your device rather than sent to our document-processing servers. Initial model setup and model updates require an internet connection and sufficient storage. Once a model is ready, core features can work offline. AI output may contain mistakes; check it against the original material. Free and Pro Basic recognition, note management, and the basic model are free, with no per-use processing charge. Optional auto-renewable SnapNote Pro subscriptions unlock advanced models, multi-page batch recognition, PDF import, custom templates, and CSV export from Ask Notes. Monthly and annual plans are available. Prices, features, and availability are shown in the app's purchase screen. Apple handles payment; manage or cancel subscriptions in your Apple Account settings. Support: https://snapnote.bitanoworks.com/en/support Privacy Policy: https://snapnote.bitanoworks.com/en/privacy Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

Gadeon runs Qwen3.5 and QwenPaw hybrid language models entirely on your device's Apple Neural Engine, using Core ML as its only framework dependency. There's no C, no Python, and no cloud calls: every token is generated locally, keeping your conversations private. Under the hood, these models mix Gated DeltaNet recurrent layers with a smaller number of attention layers. Gadeon compiles that hybrid architecture directly onto the Neural Engine's dataflow accelerator, so both prompt processing (prefill) and token generation (decode) run on-chip instead of falling back to the CPU or GPU. On an Apple Silicon Mac, prefill measures roughly 2 to 2.4 times faster and about 4.4 times more energy-efficient per token than a Metal GPU baseline, while leaving the GPU free for other work. Conversations in Gadeon are append-only: each turn extends the model's fixed-size recurrent state instead of re-processing the entire chat history, so response latency doesn't grow as a conversation gets longer. The app can also roll back to an earlier point in a conversation, dropping reasoning traces or replaying tool calls in a clean form without reprocessing everything from scratch. For ternary-quantized models, Gadeon switches to a pure-Swift Metal GPU backend behind the same session and tokenizer interface, so both compute paths feel identical from the chat UI. Gadeon is a proof of concept for bringing Gated DeltaNet hybrid models to the Neural Engine through Core ML - built to explore what's possible on Apple's own silicon.