I made an app that runs Mistral 7B 0.2 LLM locally on iPhone Pros

Re:I made an app that runs Mistral 7B 0.2 LLM locally on iPh... by jameshart on Sunday January 07, 2024 @10:09PM (#38907804)

I don't think running raw llama.cpp under termux in a shell on your phone, after downloading and compiling it from scratch,, is really comparable to 'I made an app'.

[ Parent | on HN ]

Re:I made an app that runs Mistral 7B 0.2 LLM locally on iPh... by halJordan on Sunday January 07, 2024 @11:00PM (#38908103)

Shh we're in our "Android is always better" era

[ Parent | on HN ]

Re:I made an app that runs Mistral 7B 0.2 LLM locally on iPh... by enticeing on Sunday January 07, 2024 @11:55PM (#38908431)

I don't read GP comment as saying "Android is always better", unless there's something I missed?

More options is a good thing, nobody said a manual process was better than an app.

[ Parent | on HN ]

Re:I made an app that runs Mistral 7B 0.2 LLM locally on iPh... by _andrei_ on Monday January 08, 2024 @03:33AM (#38909482)

What we're seeing here might be classic case of the iOS Freedom Choking Syndrome: when a device's lack of freedom spreads to its owner and chokes cerebral circulation.

[ Parent | on HN ]

Re:I made an app that runs Mistral 7B 0.2 LLM locally on iPh... by throwaway743 on Monday January 08, 2024 @08:53AM (#38911895)

Please keep the snarky cliche responses on other forums where they belong

[ Parent | on HN ]

Re:I made an app that runs Mistral 7B 0.2 LLM locally on iPh... by livrem on Monday January 08, 2024 @04:09AM (#38909699)

That is exactly how I ran llama on my old Android phones a few days ago. Did not even know there was documentation for it. It just worked to compile and run like on desktop. How would having an app be better? Running it in termux means I can use git to sync the wrapper-scripts and chat-templates that I have on my desktop computers to also run on the phone (but using a smaller model).

[ Parent | on HN ]