Models & downloads

Model downloads, storage requirements and optional authentication.

On-device AI needs model weights. OY.Surf downloads them on demand and shows real progress (X / total GB). You can keep working while they download.

What downloads

Description / search — a vision-language model + embedding model.
Generation — Z-Image Turbo (text-to-image / image-to-image).
Instruction editing — Qwen-Image-Edit (size shown in Settings), downloaded when requested.
Dictation — a Whisper model for Surf Flow.

Models download in the background; the app stays usable.

Faster downloads

Add a Hugging Face token in Settings → AI models to authenticate supported downloads. A stalled partial shows as paused with a Resume button.

Where they live

Weights are cached locally and reused; once downloaded, the feature works offline.