Run AI Models On-Device — Zero Config, Five Minutes

You already know why on-device AI matters. Privacy, latency, cost. You've read the guides. Now you want to actually do it. Here's what that looks like with Xybrid - no tensor shapes, no preprocessing scripts, no ML expertise. Install # macOS / Linux curl -sSL | sh # Windows (PowerShell) irm | iex Text-to-Speech xybrid run --model kokoro-82m --input "Hello from the edge" --output hello.wa That's it. Xybrid resolved the model from the registry, downloaded it, ran inference, and saved a WAV file. You configured nothing. Kokoro is an 82M parameter TTS model with 24 voices.