Alibaba also provides an OpenSource App, it even has support for their multimodal voice chat Model qwen2.5 omni:
https://github.com/alibaba/MNN

Is the chat uncensored?

Quote: "all running locally, without needing an internet connection once the model is loaded. Experiment with different models, chat, ask questions with images, explore prompts, and more!"

So you can download it and set the device to airplane mode, never go online again - they won't be able to monitor anything, even if there's code for that included.

Why would I use this over Ollama?

everything is unmonitored if you don't connect to the network.

That is exactly what Ollama does too.

Ollama can’t run on Android

That's fair, but I think I'd rather self host an Ollama server and connect to it with an Android client in that case. Much better performance.

Censoring is model dependent so you can select one of the models without the guardrails.

But not everything works in those conditions.

never go online again - they won't be able to monitor anything, even if there's code for that included.

Sounds counter-intuitive on a smart phone where you most likely want to be online again at some point in time.

Yes, that's my setup. But this will be useful for cases where internet connection is not reliable

Enclave on iOS does the trick for the rare times i need a local LLM

You can use it in termux

it does if you make it work in those conditions.

software that "phones home" is easy to fool.

Didn't know about this. Checking it out now, thanks!

Has this actually been done? If so, I assume it would only be able to use the CPU

Duck.ai doesn't data mine, and has o3 mini which I have found to be very good. Its got some extra functionality like lines to break up text.