On-device · Offline · Yours

Private AI that
runs on your phone

No cloud. No account. No tracking. Your conversations never leave your device.

0
Bytes sent to servers
~3B
Params on your chip
$4.99
Once. No subscription
Apple Intelligence built in

Zero download.
Instant answers.

On supported iPhones, iPads and Macs, privateSLM uses Apple's built-in system model through the Foundation Models framework. Install, open, chat — inference runs on the Neural Engine.

Llama · Qwen · Gemma

Bring your
own model

No Apple Intelligence? Download a small open model once and run it locally with the built-in model manager — powered by llama.cpp. Switch engines any time.

Airplane mode approved

Privacy by physics,
not by promise

No sign-up, no analytics, no ads, no server component at all. Chats live in a local database on your device. Turn the radio off — everything keeps working.

A real chat app

History. Search. Voice.
Full control.

Multiple conversations with search, edit & regenerate, voice input with spoken replies, custom system prompt and sampling. One-time purchase, family sharing included.