Local LLM runner vs Hushfox

Run LLM on your iPhone, 100% local, no network (Network needed once to download a model) Models: • Qwen2.5 0.5B Instruct — ~0.4 GB (4 GB RAM) • Llama 3.2 1B Instruct — ~0.8 GB (4 GB RAM) • Qwen2.5 1.5B Instruct — ~0.9 GB (4 GB RAM) • Llama 3.2 3B Instruct — ~1.9 GB (6 GB RAM) • Qwen3 4B Instruct 2507 — ~2.5 GB (6 GB RAM) • Qwen2.5 7B Instruct — ~4.4 GB (8 GB RAM) Also: • Add your own GGUF (for example, from Hugging Face) • Auto-estimated max context from GPU memory; you can change it Requires iOS 18 or later. Tested on iPhone 11, 14 Pro, 15 Pro with iOS 26. Qwen models © Alibaba Cloud. Licensed under Apache License 2.0. Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Built with Llama. On-device inference uses llama.cpp (MIT License).

Hushfox runs language models entirely on your phone. Nothing you type leaves the device: there is no server that could receive it, no account to create, and no cloud to sync to. Download any GGUF model from Hugging Face and start chatting. You need a connection once, to fetch the model. After that it works fully offline, on a plane, on the subway, or anywhere with no signal. Private by design Your prompts and answers stay on the device. Hushfox has no analytics SDK and no hidden network calls. A built-in log shows you exactly what, if anything, leaves your phone. Any open model Bring any GGUF from Hugging Face. On iPhone and iPad you can also run MLX models. The only real limit is your device RAM: in practice, 3B to 8B models quantized to 4 bits run on a modern phone. Long conversations that stay put Pick up a long chat instantly. Context is kept on device, so a conversation you started days ago is right where you left it. Yours to control No subscription wall to open the app. No sign-in. No tracking. You choose the model, you keep the data. Frequently asked Does it work without internet? Yes. You only need a connection once, to download a model. What models does it support? Any GGUF from Hugging Face, plus MLX on iPhone and iPad, within the limit of your device RAM. Are my conversations sent anywhere? No. There is no server that can receive them.