Chart standing · US
What changed · US
Listing changes AppTracker has observed for this app in this storefront — new versions, price moves, rating shifts, and store copy.
Bug fixes and performance improvements.
Price & rating history · US
Reconstructed from the listing changes AppTracker has observed in this storefront, so each line starts at the first change on record.
Average rating
About
LocalLLM is the private AI chat app built for beginners—run powerful language models entirely on your iPhone and iPad. No cloud, no account required, and nothing you type is ever sent to the internet. Chat offline on flights, in remote areas, or anywhere without wifi. WHY LOCALLLM? Unlike cloud AI apps that send your conversations to servers, LocalLLM processes everything on your device. Your chats, your models, your data—always under your control. FEATURES • 100% PRIVATE — Conversations and models stay on your device. No data collection. No tracking. • WORKS OFFLINE — Download a model once, chat anytime without internet. • APPLE INTELLIGENCE — On supported devices (iOS 26+), use Apple's built-in on-device AI with zero download. • CURATED MODELS — Llama 3.1 & 3.2, Qwen 2.5 & Qwen 3.5, Gemma 3, DeepSeek R1, Mistral, Phi 3.5, and more. From fast 1B models to powerful 12B. • BACKGROUND DOWNLOADS — Download models while using the app. Pause, resume, or delete anytime. • CHAT HISTORY — All conversations saved locally. Browse, search, resume, or clear from Settings. • STREAMING RESPONSES — Watch replies appear in real time for a natural chat experience. • BEGINNER-FRIENDLY — Step-by-step onboarding, device check, and plain-language guidance. No jargon, no account signup. PERFECT FOR • Privacy-conscious users who want AI without sharing data • Travelers who need AI on planes and in areas with no signal • Students and professionals who want coding, writing, and brainstorming help offline • Anyone trying local AI for the first time SUPPORTED MODELS Small & fast: Llama 3.2 1B/3B, Qwen 3.5 0.8B/2B, DeepSeek R1 1.5B, Gemma 3 4B, Phi 3.5 Mini Standard: Llama 3.1 8B, Qwen 2.5/3.5 4B/7B, DeepSeek R1 8B, Mistral 7B, Gemma 2 9B Large: Qwen 3.5 122B MoE (for high-end devices) FREE vs PRO Free: One downloaded model plus Apple Intelligence when available. Pro: Unlimited models, background downloads, and future premium features. HOW IT WORKS 1. Open the app—no account needed 2. Choose Apple Intelligence or pick a model from the Models tab 3. Download your model (one-time, over wifi) 4. Chat privately, offline, anytime Run a local LLM on your iPhone. Private AI chat without the cloud. Your AI, your device, your rules. Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Privacy Policy: https://ai-assist-virid.vercel.app/privacypolicy.html
What's new · 1.9
Bug fixes and performance improvements.
Details