FishLLM vs ArcanAI

FishLLM runs LLMs locally on your device. FishLLM makes it possible to chat with LLMs without leaking personal data. FishLLM makes deploying the latest LLM on your device as easy as a few clicks. Maximize the potential of the M1/M2/M3/M4/M5 chips on your device. Run LLMs like: gpt-oss, Qwen3, Gemma3, DeepSeek, ChatGPT, LLaMa. ——— #Features: ■ Run a state-of-the-art GPT model locally on your device with just one click. No data uploads, ever! ■ Easily update to the latest open-source GPT model to stay on the forefront of AI technology. ■ Access your AI assistant anytime, anywhere - even offline! ■ Configure a LLM（large language model）to run directly on your device with just a few clicks ■ Simple and easy to use, no complicated jargon or troublesome setup, almost plug-and-play. ---- FishLLM Usage Requirements: We offer a 7-day free trial. After the trial ends, you will need to subscribe or make a one-time purchase of the Premium version in order to continue using FishLLM. Subscription Agreement and Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Privacy Notice: https://fish.bluepill.life/privacy.html

ArcanAI is a private, on-device AI chat app that runs open-source language models entirely on your iPhone or iPad. No accounts. No subscriptions. No cloud. No internet required. Import any GGUF model from Hugging Face and start chatting — every conversation happens locally, powered by hardware-accelerated inference using Apple's Metal framework. Your messages never leave your device. KEY FEATURES - Run AI models 100% offline — on a plane, off the grid, anywhere - Import any GGUF model from Hugging Face — choose the size and capability that fits your device - Store and switch between up to 5 models at once - Analyze documents — upload PDFs, spreadsheets, text files, CSVs, and more - GPU-accelerated inference for fast, streaming responses - Full conversation history with multiple independent chats - Edit messages and regenerate responses - Customize temperature, max tokens, and system prompts - Beautiful dark UI with markdown-rendered responses - Text-to-speech support SUPPORTED MODEL FAMILIES Llama, Gemma, Mistral, Phi, Qwen, and any ChatML-compatible model. RECOMMENDED STARTER MODELS - Llama 3.2 1B (~570 MB) — great for older devices - Gemma 2 2B (~1.0 GB) — balanced performance - Qwen 2.5 3B (~1.5 GB) — multilingual and code capabilities PRIVACY FIRST Zero data collection. Zero telemetry. Zero crash reporting. Zero cloud sync. Your conversations and model files stay on your device — always.