# RunAnywhere — RunAnywhere SDK: On device AI > Private, on-device AI assistant for chat, voice, and text processing. (iPhone/iPad app by RunAnywhere.) - Source: https://appshunter.io/ios/app/runanywhere/id6756506307 (this page in markdown: same URL + `.md`) - Developer: [RunAnywhere](https://appshunter.io/developer/1861025187) - Category: Developer Tools, Productivity - Price: Free - Rating: 4.30/5 from 4 App Store ratings - Age rating: 4+ - Requires: iOS 17.5 · 79 MB - Languages: American English - Released: 2025-12-18 - Data updated: 2026-08-24 - Monetization: free - User reviews in markdown: https://appshunter.io/ios/app/runanywhere/id6756506307/reviews.md ## What is RunAnywhere? RunAnywhere brings private, on-device AI to your iPhone and iPad. Download a model once, then chat, transcribe speech, and generate natural-sounding audio locally, even when you are offline. PRIVATE AI IN ACTION Ask questions, summarize ideas, draft text, and have useful conversations without sending every prompt to a remote AI service. VOICE, END TO END - Turn speech into text with compact Whisper models - Listen to natural text-to-speech with Piper voices - Use a voice assistant that connects listening, reasoning, and speaking CHOOSE THE RIGHT MODEL Choose compatible models across llama.cpp, ONNX, and MLX runtimes. Model availability and performance vary by device. BUILT FOR PRIVACY AI inference runs on your device, reducing the need to send prompts or audio to a remote model service. WORK OFFLINE After downloading your selected models, core AI experiences can run without Wi-Fi or cellular data. RunAnywhere is your private AI companion for everyday writing, voice notes, reading aloud, and offline conversations. ## Key features - On-device AI processing - Offline functionality - AI Chat - Voice to Text transcription - Text to Speech conversion - Hands-free voice assistant ## Frequently asked questions about RunAnywhere ### Does RunAnywhere have ads? No, RunAnywhere does not contain advertisements. The app is completely free and ad-free, allowing for an uninterrupted user experience. ### What devices does RunAnywhere support? RunAnywhere is available on Mac, iPhone, and iPad. This broad compatibility allows users to access its features across multiple Apple platforms. ### How often is RunAnywhere updated? The latest version of RunAnywhere is 0.30, which was last updated on March 18, 2026. Updates are released to improve functionality and add new features. ### What is the age rating for RunAnywhere? RunAnywhere has an age rating of 4+. This indicates it is suitable for users of all ages, with no mature content. ### Can I use RunAnywhere without an internet connection? Yes, RunAnywhere is designed to work entirely offline. All AI processing happens on your device, meaning no internet connection is required for any of its features. ### Does RunAnywhere collect my data? No, RunAnywhere prioritizes privacy. All AI processing occurs on your device, and your conversations never leave your phone. There is no cloud storage or data collection. ### What are the main features of RunAnywhere? RunAnywhere offers AI chat, voice-to-text transcription, text-to-speech conversion, and a hands-free voice assistant. These features are all processed locally on your device. ### What is the user sentiment for RunAnywhere? RunAnywhere has received excellent user feedback, with a rating of 5.0 stars from 3 ratings. This indicates a very positive reception from its current user base. ## Version history (last 5 releases) ### 0.39 — 2026-08-18 Adds new on-device model support, refreshes AI dependencies, and improves compatibility and reliability across chat, voice, and model management. ### 0.38 — 2026-08-14 This update improves reliability and compatibility for private, on-device AI workflows across chat, voice, and model management. ### 0.37 — 2026-08-05 This release adds support for LFM 2.5. The model runs entirely on device on the Apple Neural Engine, and can also be run on the CPU and the GPU so you can compare how the same model behaves on each. Note: LFM 2.5 is a large download and needs a healthy amount of free space, since it is compiled and cached on device after the first load. The first response to a prompt can take a moment to begin; once it starts, it streams quickly. ### 0.36 — 2026-07-25 New family of NVIDIA models added within llama.cpp + MLX support, plus various bug fixes. ### 0.34 — 2026-07-17 • Updated the on-device AI runtime and model catalog. • Added Bonsai 1-bit model support and improved model filtering. • Improved benchmark aggregation and variance reporting. • Added RAG streaming and multi-turn tool-calling history. • Fixed model downloads, chat cancellation, voice/TTS, and stability issues. ## More apps by RunAnywhere - [YapRun](https://appshunter.io/ios/app/yaprun/id6759540170) All apps by RunAnywhere: https://appshunter.io/developer/1861025187 --- *Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-24.*