How can we help?
Mura runs entirely on your iPhone, so most things just work — but if you're stuck, we're here. Check the quick answers below, and reach out any time if you still need a hand.
1.Contact us
To help us resolve things faster, please include your device model, your iOS version, your Mura app version, and — if it's about a specific model — which model you were using. Never include anything sensitive: your conversations stay on your device and we have no way to access them.
2.Common questions
Which models does Mura support?
Mura supports leading open models including Meta Llama 3.2, Google Gemma 3, Qwen3, Microsoft Phi-4 mini, Mistral 7B, SmolLM3 and DeepSeek R1 — plus Apple Intelligence on supported iPhones. Every downloaded model runs completely offline on your device, and the catalog keeps growing.
Does Mura work without internet?
Yes. Once a model is downloaded, Mura works completely offline. The only time a connection is needed is the one-time model download — after that, all chatting happens locally.
A model won't download or keeps failing
Model files are large and are fetched directly from Hugging Face. Make sure you're on a stable Wi-Fi connection with enough free storage, then retry the download. If it still fails, email us with the model name and we'll look into it.
Which devices are supported?
Mura is built for iPhone and optimized for Apple silicon. It runs on iOS 26 and later; larger models need a more recent iPhone with enough memory, so Mura's catalog tells you exactly which models fit your device. The built-in Apple Intelligence option requires an Apple Intelligence-capable iPhone.
Is my data private?
Your conversations are processed entirely on your device — there's no account, no cloud sync, and nothing is ever used to train a model. See our Privacy Policy for the full detail.