Need Help?
I personally respond to every support request. Usually within 24 hours.
mergisi@gmail.comOnDevice LLM — FAQ
How do I get started?
Tap the model icon (top left) to open the model list. Choose a model and tap "Download". Gemma 2 2B (1.6 GB) is the fastest download. Once downloaded, tap "Load" and start chatting.
Which iPhone models are supported?
iPhone 13 or newer is recommended for best performance (6GB RAM). The app runs on any iPhone with iOS 17+, but larger models may run slowly on older devices. iPhone 15 Pro and newer provide the best experience.
Why are model files so large?
AI language models contain billions of parameters compressed into GGUF format. Smaller models (1-2 GB) work well for basic tasks. Larger models (3-5 GB) provide better quality responses. All models are downloaded once and stored locally.
Does the app work offline?
Yes! After the initial model download, the app works completely offline. No internet connection is required for conversations.
What is Pro and what does it include?
Pro unlocks: unlimited model switching, unlimited chat history, custom system prompts, and HuggingFace model browser. Free tier includes 1 model and limited chats.
How do I restore my purchase?
Open the app → Settings (⋯ icon) → Restore Purchases. Make sure you're signed in with the same Apple ID used for the original purchase.
The model output looks wrong / garbled
This can happen if a model file was corrupted during download. Try deleting the model (swipe left in the model list) and downloading again. If the issue persists, try a different model.
How do I delete a downloaded model?
Open the model list (top left icon) → swipe left on any installed model → tap Delete. This frees up storage space.