Join waitlist
Back to products
Apollo AI

Apollo AI

Run local models like Llama on iOS

Website apps.apple.com
Overview

What it is

Apollo AI is an app for running local models like Llama or Qwen privately on your iOS device. Once downloaded, these models can be used offline with no internet connection at all. Try Llama 3.1, Qwen, Deepseek r1 Distillations, and more. Since these run on your phone they're completely free to keep using.

Intent

I need it when

Host a private, family-friendly AI chatbot alternative to commercial services

Apollo's custom backend support lets users run their own LLM on a home computer and connect via the mobile app, creating a private ChatGPT-like experience for family members without external API costs

Chat with multiple AI models without vendor lock-in or subscription fees

Apollo lets users connect to OpenRouter, local LLMs via LEAP, or custom backends (LM Studio, Ollama), enabling access to Meta Llama 3, ChatGPT-4, and other models from one app without monthly fees or dependence on a single provider

Experiment with different AI models and providers from a mobile device

Apollo provides a unified client interface to switch between local models, OpenRouter's 100+ models, and custom backends, letting users test and compare different AI systems without installing separate apps

Access AI capabilities with text-to-speech and speech-to-recognition features

Apollo integrates on-device and third-party TTS/STT (including ElevenLabs support), enabling voice-based AI interaction on mobile devices for hands-free conversations and accessibility

Run AI models privately on-device without sending data to cloud servers

Apollo supports on-device LLM execution via LEAP technology, allowing users to run smaller language models securely on iPhone, iPad, or Mac with full privacy and no data transmission to external servers

Drop

Not a fit when

  • User requires guaranteed current event knowledge—local LLMs have knowledge cutoff dates and may provide outdated information
  • User needs enterprise-grade voice API integration—ElevenLabs voice list loading is unreliable per user reports
  • User wants hands-free operation without screen—app does not support background operation or CarPlay integration
  • User requires seamless cross-device sync—recent updates introduced iCloud sync bugs affecting multi-device users
  • User lacks technical setup skills—custom backend configuration (LM Studio, Ollama) requires advanced setup knowledge
Commercials

Pricing

Free app with optional paid API integrations (OpenRouter, custom backends) View pricing