Model Zoo
An on-device AI playground for iPhone and iPad.
Browse a curated catalog of open-source on-device AI models, download any of them with one tap, and run them fully on-device — no server, no account, nothing leaves your phone.
What you can do
- Chat with small multimodal language models (Gemma, etc.) — text + image in, text out.
- Generate images from a prompt with Hyper-SD.
- Remove backgrounds, matte video subjects, and colorize old photos.
- Estimate depth and reconstruct 3D faces from a single photo.
- Detect and classify with YOLO, SigLIP, and open-vocabulary zero-shot detectors.
- Separate music stems with Demucs and transcribe audio to MIDI with Basic Pitch.
- Synthesize speech and clone voices with Kokoro and OpenVoice.
- Super-resolve low-res images with SinSR and spot defects with EfficientAD.
Every model links back to its original paper, repository, and license.
Privacy first
- All inference runs locally on your device.
- The app fetches model files anonymously over HTTPS from public storage.
- No analytics, no ads, no account.
Read the full Privacy Policy.
Need help?
Visit the Support page for FAQs and contact info.
Links
© 2026 Daisuke Majima