PrivAI LLM - Local AI Chat
阳 孙
PrivAI runs AI language models entirely on your iPhone. Download a model once, then chat offline — nothing you type is ever sent to a server. Pay once, no subscription, no account required. FEATURES Private by design — conversations are processed and stored on your device. No account, no cloud. Works offline — after the one-time model download, works even in Airplane Mode or with no Wi-Fi. Choose your model — supports Qwen3.5, Qwen3, Gemma 3, Llama 3.2 with automatic memory checks. Advanced users can load any MLX model by HuggingFace ID. Deep-thinking mode — collapsible step-by-step reasoning trail (Qwen3 / Qwen3.5). History — search, star and reuse past prompts. Prompt templates — translate, summarize, polish writing, draft emails. Photo to text — capture text from paper documents with the camera. Download mirror — set a custom mirror URL if HuggingFace is slow in your region. GOOD TO KNOW Models are about 0.4–3 GB, so Wi-Fi is recommended for the first download. Larger models need more memory; if the app closes while generating, pick a smaller model. AI output may be inaccurate — check important information.