Run Llama, Gemma, Qwen, DeepSeek, and more locally on your iPhone, iPad, and Mac. Offline. Private. No login. Optimized for Apple Silicon.




PocketPal is described as 'An app that brings language models directly to your phone' and is a AI Chatbot in the ai tools & services category. There are more than 50 alternatives to PocketPal for a variety of platforms, including Web-based, Mac, Windows, Android and Linux apps. The best PocketPal alternative is ChatGPT, which is free. Other great apps like PocketPal are Lumo by Proton, Mistral Le Chat, Ollama and Google Gemini.
Run Llama, Gemma, Qwen, DeepSeek, and more locally on your iPhone, iPad, and Mac. Offline. Private. No login. Optimized for Apple Silicon.




Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.
Ultra-minimal personal AI agent: starts small, self-modifies its code live, adapts by writing exactly the code & features you need.






The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.




Kai is designed to provide you with access to powerful, state-of-the-art conversational AI models. Through a simple and intuitive chat interface, you can engage with models like Llama and Google's Gemini, exploring their capabilities for various tasks.




Witsy is a BYOK (Bring Your Own Keys) AI application: it means you need to have API keys for the LLM providers you want to use. Alternatively, you can use Ollama to run models locally on your machine for free and use them in Witsy.




An AI-powered chat interface designed for exploring advanced topics like quantum computing, programming, and emerging AI trends through interactive conversation.




AI Chat Assistant is a free web-based tool that allows students and learners to chat with AI, practice languages, get instant explanations, and boost productivity.The platform is fully online and also available as a Progressive Web App (PWA), so you can use it on mobile or...




Native, Apple Silicon–only local LLM server. Similar to Ollama, but built on Apple's MLX for maximum performance on M-series chips. SwiftUI app + SwiftNIO server with OpenAI-compatible endpoints.

Paperclip by FireCube (formerly known as Clippy by FireCube) brings back the infamous Clippit companion into your desktop powered by a Large Language Model AI to chat with. The app is completely free to use and open source.
