FAQ
Questions, answered.
It mostly comes down to one idea: the model runs on your device, so nothing leaves it. Here's the rest.
Still have a question?
Ask on GitHubIs it really free?
Yes. Quenderin is MIT-licensed open source, and inference runs on your own hardware—so there are no token costs and no subscription.
Is my data sent anywhere?
No. After the one-time model download, Quenderin makes no network calls. There are no analytics, no accounts, and no telemetry. Because it's open source, you can verify this yourself.
What devices does it run on?
Quenderin is on the App Store for iPhone today, and the desktop app runs on macOS and Linux. A native Android app is in active development—the same hardware-detection and model-selection engine, rebuilt natively for performance.
Do I need a powerful phone?
No. Quenderin scales from a Raspberry Pi to an M-series Mac. It detects what your device can handle and recommends a model that actually runs—down to a 0.4 GB ultra-light build.
Which models can it run?
Any GGUF model on llama.cpp—Llama, Qwen, DeepSeek, Mistral, Gemma, Phi, and thousands more from Hugging Face. See the model catalog for the curated shortlist it recommends from.
Can it actually do things, or just chat?
Yes — a lot. On a Mac it can organize files, drive apps, and run your Apple Shortcuts (the launch post has the details). It's a governed agent: it asks before every change, keeps a local log you can review, and can undo a whole task. A hard safety blocklist it can't override means it will never autonomously pay, delete, transfer money, or touch credentials.
Can the agent mess up my computer?
By design, it's hard to. Nothing that changes anything runs without your explicit yes for that step; file tasks are limited to a folder you grant, and never overwrite or truly delete (things move to a visible Trash you can restore from). You can stop it instantly with Ctrl-C, and quenderin undo reverses the last task — even in a new session, an hour later. Want to look before you leap? --dry-run shows exactly what it would do while changing nothing.
How big is a model download?
Your choice—from about 0.4 GB for the ultra-light build to 9 GB for the flagship. It downloads once over Wi-Fi and resumes in the background if interrupted.
When can I install it?
The iPhone app is on the App Store now, free. The desktop is open source and runnable from GitHub today, and a native Android app is on the way—star or watch the repo on GitHub to hear the moment it lands.
Bring your AI offline.
It's open source and runs from GitHub today. Star the repo to follow along.