Available on iPhone

OnDevice LLM

Run Gemma, Llama, Qwen and 1000+ open-source AI models 100% offline on your iPhone. No internet, no API keys, no cloud.

Download on the App Store

Built for Privacy

🔒

100% Offline

Your conversations never leave your iPhone. No server, no logs, no telemetry.

⚡

Metal GPU Acceleration

Apple Silicon-powered inference. 40+ tokens per second on iPhone 15 Pro.

🤖

1000+ Models

Run any GGUF model from HuggingFace. Gemma, Llama, Qwen, Mistral, and more.

✈️

Works Anywhere

Planes, subways, mountains. AI that works wherever you are, no signal needed.

♾️

No Rate Limits

Chat as much as you want. No usage caps, no throttling, no monthly costs.

🎭

Custom Personas

Define your AI's role with custom system prompts. Your AI, your rules.

Featured Models

Gemma 4 E4B IT Gemma 4 E2B IT Gemma 2 2B IT Llama 3.2 3B Qwen 2.5 3B SmolLM2 1.7B Phi-4 Mini DeepSeek R1 1.5B + Any GGUF Model
🛡️

Zero Data Collection

OnDevice LLM does not collect, transmit, or store any of your conversations. Everything runs locally on your device. We have no servers, no accounts, and no access to your data — ever.