Your AI, your rules.

One app for every model

Local models when you want privacy. Cloud providers when you need power. Switch freely, no lock-in, no sign-in.

macOSApple Silicon & Intel, macOS 15.7
iPhone & iPadiOS 18.6
🏠
Local Models

Privacy First

Llama, Gemma, Qwen and more run directly on your device via llama.cpp. Nothing leaves your iPhone or Mac.

  • Llama, Gemma, Qwen, Falcon & more
  • No internet required
  • Automatic download & progress tracking
Cloud Providers

Connect Your Way

Your own API keys, direct connections to Google, Groq, OpenRouter, Cerebras, and GitHub Models. No middlemen.

  • Google Gemini, Groq, OpenRouter
  • Cerebras, GitHub Models
  • Switch providers on the fly
💬
Chat UI

Conversations that Flow

Native markdown with code blocks, full session history, and instant model switching mid-conversation.

  • Full markdown & code blocks
  • Session management & search
  • Conversation context display
Performance

Built for Speed

Hardware-accelerated inference, low memory footprint. Snappy whether you're running on-device or hitting a cloud API.

🌟
Customizable

Made for You

Text size, reasoning effort, markdown rendering, spell check, every detail configurable. API keys stay in the system Keychain.

🧠
Reasoning

Think Before Answering

Enable reasoning mode on compatible models for step-by-step thinking on harder problems. Works locally and with cloud providers that support it.

Beautiful on every device

Crafted for iOS and macOS with full light and dark theme support.

im.ai iOS light theme
Light theme
im.ai iOS dark theme
Dark theme

See it in action

Fluid conversations Compare models instantly Your choice of provider Hundreds of free models Organized session history Tuned to your taste

Fluid conversations

Full markdown with code blocks. Ask anything. Responses are clear, readable, and beautifully formatted.

Compare models instantly

Run the same prompt across multiple models and see answers side by side. Pick the best for the job.

Your choice of provider

Switch between Local, Google, Groq, OpenRouter, Cerebras, and GitHub. Any prompt, any time, no lock-in.

A world of free models

Access Gemma, Llama, Qwen, and free cloud tiers. Many models need no API key at all. Start exploring immediately.

Organized session history

All conversations saved, searchable, and organized by date. Context carries forward so you can pick up where you left off.

Tuned to your taste

Markdown rendering, reasoning effort, text size, spell check, every detail is yours to configure.

Privacy and Security

Local

Models run entirely on your device via llama.cpp. No network connection is made. Nothing leaves your iPhone or Mac.

Remote

Bring your own API key. im.ai connects directly from your device to Google, Groq, OpenRouter, Cerebras, or GitHub Models. No relay, no proxy, no im.ai servers in the path.