Droppp vs Gadeon

Droppp is a simple local file transfer app for iPhone and iPad that works over Wi-Fi and Personal Hotspot. Use Droppp when AirDrop is not available, cable transfer is inconvenient, or you do not want to upload files to the cloud. Connect both devices to the same Wi-Fi network, or connect the other device to your iPhone or iPad’s Personal Hotspot. Transfer files through a browser without installing any extra desktop program. Turn on the local file drop server in Droppp, then open the displayed address in a browser on another device. You can also scan the QR code or change the server port. Keep Droppp open with your device’s screen on during transfers. Drag and drop or choose photos, videos, documents, ZIP files, and more on the web page. Received files are saved locally inside Droppp and can be viewed, shared, deleted, or moved to other apps. Select multiple files and drag them to apps that support drag and drop. Folders make it easier to organize incoming files. Create named folders and nested folders, then drag files or folders where they belong. Share or delete folder contents in Droppp, and view or download them from the local web viewer. Access Droppp’s Files folder in Apple’s Files app and copy files between it and Droppp storage. You can also link folders from the Files app, including iCloud Drive folders. Changes to files in a linked folder apply to the original folder. View its files, upload new files, and download them through the web viewer too. Droppp works without accounts or login. Files are transferred directly between devices over your local connection, without requiring cloud upload. History Insights helps you review recent transfer activity. You can disable history recording in Settings when you do not need it. Key Features - Transfer files through a browser over Wi-Fi or Personal Hotspot - Send files directly to your iPhone or iPad - Drag and drop or choose files to upload - Store received files locally inside Droppp - View, share, delete, and organize saved files - Create named folders and nested folders - Copy files between Droppp storage and Files - Link folders from the Files app, including iCloud Drive - Select multiple files and drag them to other apps - Drop files from other apps into Droppp - View and download files and folder contents from the web - Create TXT files and URL links from the web page - Check recent activity with History Insights or disable recording - No account, login, or cloud upload required - Quick guide in Settings > Help Useful for - Sending files from a Windows PC to iPhone - Moving files from Android, Mac, tablets, or other devices to iPad - Receiving files without cables, messengers, or cloud storage - Keeping transfers inside your local network - Collecting temporary files, work files, photos, and documents Feedback: brick@pixelbricktek.com Privacy Policy: https://pixelbricktek.github.io/Droppp/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.