r1o

Private Pocket LLM

Run AI on your own Apple Silicon. No cloud. No APIs. No compromise.

Download for macOSmacOS (Apple Silicon)
v0.1.0

Why r1o

Private by default

Your inference never leaves your network. No telemetry, no cloud calls, no third-party APIs. Full sovereignty over your data.

Apple Silicon native

MLX-optimized runtime that leverages the Neural Engine and unified GPU. Built specifically for M-series chips.

Cluster-ready

Orchestrate inference across multiple Macs over Thunderbolt or Tailscale mesh. Scale with hardware you already own.

Open source

Full stack is open. Your hardware, your models, your rules. Inspect every line of code that touches your data.

How it works

01

Download r1o

Install the macOS app on any Apple Silicon Mac. One binary, no dependencies.

02

Point it at your models

Load GGUF or MLX models from disk. Supports Llama, Mistral, Qwen, and more.

03

Chat privately from any device

Connect from iPhone, iPad, or another Mac over Tailscale. Your AI, everywhere.