# Local AI Chat - pocket — Local Offline Private AI Chat > Offline private AI chat and image generation on-device. (iPhone/iPad app by Rica Harz.) - Source: https://appshunter.io/ios/app/local-ai-chat-pocket/id6476791661 (this page in markdown: same URL + `.md`) - Developer: [Rica Harz](https://appshunter.io/developer/1721229443) - Category: Productivity, Education - Price: Free with in-app purchases - Rating: 4.40/5 from 65 App Store ratings · 46 written reviews indexed - Age rating: 12+ - Requires: iOS 18.6 · 245 MB - Languages: Canadian French, German (Germany), American English, Arabic, Chinese (Simplified, China), Chinese (Traditional, Taiwan), Korean, Danish, Latin American Spanish, Hebrew and 13 more - Released: 2025-01-16 - Data updated: 2026-08-13 - Monetization: free with in-app purchases - User reviews in markdown: https://appshunter.io/ios/app/local-ai-chat-pocket/id6476791661/reviews.md ## What is Local AI Chat? Pocket: the simplest way to use private LLMs. It works fully offline and ensures your privacy when you don’t have an internet connection. Pocket runs models on-device, optimized for Apple Silicon to provide fast and efficient performance. Run powerful AI models like Llama, Gemma, and Qwen directly on your iPhone and iPad. Completely offline. 100% private. No accounts, no logins, and zero data collection. Your data never leaves your device. Personalize your experience: adjust the theme, fonts, and system prompt directly within the app to match your preferences. With Pocket's shortcut integration, you can easily chat with your local model or get an output to use with other actions, all while keeping everything local and secure. Free, local, private — your data stays on your device, always. Pocket supports a wide range of models to cater to various needs, including the following language models: Llama 3 2 1B 4bit Llama 3 2 3B 4bit Llama 3 8B 4bit Mistral 7B Instruct 02 Mistral 7B v02 4bit Phi 4bit Gemma 2 2B IT 4bit Gemma 2 9B IT 4bit Gemma 2B Quantized OpenELM 270M 4bit Qwen 3 Deepseek Whether you're working on text generation, language processing, or complex tasks, Pocket has a model for you. In addition to language models, Pocket also supports image models for users who want to generate visual content. With just a few taps, users can switch between text and image models, creating everything from written outputs to images—all processed locally on your device. Customization is key: you can easily choose a new model or switch between existing ones within the app. Whether you’re switching between models to experiment with different capabilities or looking for specific output types, Pocket gives you full control. With the ability to generate images when desired, Pocket can assist in visual projects alongside text-based tasks. All of this is done securely and privately, ensuring no data is stored or shared outside the app. You may purchase an auto-renewing subscription through an In-App Purchase. • Auto-renewable subscription • pocket plus • 1 week ($6.99) duration • 1 month ($14.99) duration • 1 year ($99.99) duration • Your subscription will be charged to your iTunes account at confirmation of purchase and will automatically renew (at the duration selected) unless auto-renew is turned off at least 24 hours before the end of the current period. • Current subscription may not be cancelled during the active subscription period; however, you can manage your subscription and/or turn off auto-renewal by visiting your iTunes Account Settings after purchase • Terms of use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ • Privacy Terms: https://oneai.framer.website/privacy ## Key features - Offline AI model execution - Private and secure data handling - Supports Llama, Gemma, Mistral, and more - On-device image generation - Customizable themes and fonts - Shortcut integration ## Pricing and in-app purchases Base price: Free. **Subscriptions** | Subscription | Price | Period | | --- | --- | --- | | Pocket Plus Yearly | $49.99 | per year | | Pocket Plus | $12.99 | per month | | Weekly | $6.99 | per 7 days | ## Recent user reviews (10 of 46) All indexed reviews: https://appshunter.io/ios/app/local-ai-chat-pocket/id6476791661/reviews.md ### 1/5 — Limit for local models *2026-06-18* The sub limits you to cheaper obscured models and throttles you by focing lower context so you end up paying more than youd pay using an API yourself rather than saving money. ### 3/5 — Potentiel mal optimiser *2026-05-04* Pocket marche bien avec les modele cloud et r est tres agreeable mais cequi me derange et ma pousser a supprimer l’app est que malgre que j’ai installé un petit modele local pocket a peine mon message envoyer a crash ce qui a fait de sa une experience gahe car app non optimiser. ### 1/5 — Sucks! *2026-03-21* Current chat will just gone if you swipe open side bar when it’s generating. It’s sucks! Disappointed! Plus; switching model bar keeps wink whenever you open it. ### 5/5 — Navy *2026-02-01* It's great ### 2/5 — Why Is There A Limit for local models? *2026-01-30* I’m Running it On My Device And Yet I Have To Pay To Continue Chatting The UI Is Good But App Isn’t ### 1/5 — Attention payant *2026-01-25* Attention,,, on vous fait tout télécharger à la fin on vous dit que c’est gratuit pendant trois jours mais c’est payant ### 5/5 — Nice *2025-11-30* အရမ်းမိုက်တယ် ဒီ App က ### 5/5 — Overall Positive *2025-11-20* Great app for just using offline LLM models for on to go research. UI/UX is really user friendly to use, like easy navigation, simple chatting, and a lot more. I recommend this as a more of a ChatGPT alternative with a similar UI. ### 3/5 — Gute Idee, es muss aber noch weiter daran gearbeitet werden ! *2025-11-14, version 0.3.9* Folgende NEUN „lokale Module“ funktionieren bei mir leider nicht bzw. lassen sich nicht oder nur teilweise herunter laden oder stoppen mittendrin einfach das Download. Manche davon bringen die App sogar zum kompletten Absturz. BITTE NACHBESSERN ! DANKE 👍🏻 -Liquid LFM2-8B-A1B -Llama 3.2 1B Instruct (das Zweite) -Deepcogito Cogito V1 Preview Llama 8B -Mistral 7B Instruct VO.3 -Hermes 2 Pro Mistral 7B -Phi 3.5 Mini 4K -Josiefied Qwen2.5 0.5B Instruct Abliterated V1 Float32 -Josiefied Qwen2.5 0.5B Instruct Abliterated V1 Float16 -Mistral Nemo Instruct 2407 ### 1/5 — clickbait *2025-11-04* They claimed that this model would work without the Internet, but with any offline request the AI ​​returns an error. 1 star ## Frequently asked questions about Local AI Chat ### What does this app do? This app allows you to run powerful AI language and image models directly on your iPhone or iPad, completely offline. It ensures your privacy by processing all data on your device without requiring an internet connection or any data collection. ### What are the key features? Key features include running AI models locally and offline, ensuring 100% privacy, supporting a wide range of language and image models like Llama and Gemma, offering customization options for themes and fonts, and integrating with Shortcuts for enhanced usability. ### How much does the app cost? The app is free to download and use with its core offline AI capabilities. However, it offers an auto-renewing subscription called 'pocket plus' for additional features, with weekly, monthly, and yearly options available through in-app purchases. ### What devices is this app compatible with? The app is optimized for Apple Silicon and runs on iPhones and iPads. It leverages on-device processing for fast and efficient performance on these devices. ### What are common use cases for this app? Common use cases include text generation for writing assistance, language processing for analysis, complex task execution, and generating visual content through image models, all while maintaining complete privacy and offline functionality. ## Version history (last 5 releases) ### 0.5.6 — 2026-05-27 Bug fixes and performance improvements. ### 0.5.5 — 2026-05-17 Bug fixes and performance improvements. ### 0.5.4 — 2026-05-03 Bug fixes and performance improvements. ### 0.5.3 — 2026-04-15 Bug fixes and performance improvements. ### 0.5.2 — 2026-04-05 Add Gemma 4 E2B and E4B on supported devices. ## Apps similar to Local AI Chat | App | Rating | Price | Category | | --- | --- | --- | --- | | [Local Chat: Private AI Chatbot](https://appshunter.io/ios/app/local-chat-private-ai-chatbot/id6504043428) | 4.5 (56) | Free | Productivity | | [Secret AI: Local AI Chat](https://appshunter.io/ios/app/secret-ai-local-ai-chat/id6744668980) | 4.4 (68) | Free | Productivity | | [Enclave - Local AI Assistant](https://appshunter.io/ios/app/enclave-local-ai-assistant/id6476614556) | 4.7 (1,029) | Free | Productivity | | [Nidum: Local AI](https://appshunter.io/ios/app/nidum-local-ai/id6737910747) | 2.6 (5) | Free | Productivity | | [LLMConnect • AI Chat](https://appshunter.io/ios/app/llmconnect-ai-chat/id6737247302) | 3.5 (4) | Free | Productivity | | [AlevioOS - Local Ai](https://appshunter.io/ios/app/alevioos-local-ai/id6749600251) | 3.0 (7) | Free | Productivity | ## More apps by Rica Harz - [AI Video - Prompt to Video](https://appshunter.io/ios/app/ai-video-prompt-to-video/id6746383690) - [Photo Cleaner - PhotoSwipe](https://appshunter.io/ios/app/photo-cleaner-photoswipe/id6748684876) - [Rush.io - Color Match Game](https://appshunter.io/ios/app/rushio-color-match-game/id6749572873) - [Aura - Quit smoking & vaping](https://appshunter.io/ios/app/aura-quit-smoking-and-vaping/id6754848968) - [mochii - Emochi alternative](https://appshunter.io/ios/app/mochii-emochi-alternative/id6759097893) All apps by Rica Harz: https://appshunter.io/developer/1721229443 ## Related topics [aibi pocket](https://appshunter.io/ios/topics/aibi-pocket) · [local ai chat](https://appshunter.io/ios/topics/local-ai-chat) · [Pocket AI](https://appshunter.io/ios/topics/pocket-ai) · [the pocketpal](https://appshunter.io/ios/topics/the-pocketpal) · [pocket pal ai](https://appshunter.io/ios/topics/pocket-pal-ai) --- *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 2026-08-13.*