Punk Labs 2026

Hopr HOPR

Private AI, on your device.
The only winning move is privacy.

Hopr runs open large language models — and image-generation models — entirely on your iPhone. No cloud, no account, no data collection. Download a quantised open model once, then chat or generate images fully offline, powered by Apple MLX.


How it works

  1. 01 Pick a model. Choose from a curated library of iPhone-grade chat models, or an image model for text-to-image.
  2. 02 Download it once. The model streams straight from Hugging Face to your device — the only network request Hopr ever makes.
  3. 03 Go offline. Every prompt, response, conversation, and generated image stays on your phone. Nothing leaves it. Ever.

On screen

Hopr home screen with the tagline: the only winning move is privacy.
Open a chat. No sign-in.
Hopr chat model library — Qwen3, Llama 3.2, Gemma, Phi 3.5 with download sizes.
A curated chat-model library.
Hopr image model list — SDXL-Turbo, SD-Turbo, DreamShaper XL Turbo, Stable Diffusion 2.1.
On-device image generation.
Hopr settings — temperature, top-p, top-k, min-p and other sampling controls.
Full control over generation.

What's inside


Requirements

Device
iPhone 15 or newer (~6 GB+ RAM), iOS 18+
Engine
Apple MLX — inference runs on the GPU of a real device
Download
Chat models from ~0.7 GB; image models several GB
Network
Needed once, to fetch a model. Everything after is offline
Get it
Available now on the App Store