My iPhone 16 Pro Max produces garbage output when running MLX LLMs

Post by fragmede » Mon, Feb 02, 2026, 2:12 PM UTC

throwaway132448 wrote: post #174

RulerOf wrote: post #150

Earlier quoted context omitted.

There was a magical period. I suspect it ended with the introduction of the Secure Enclave. But maybe it was a little later. An encrypted iTunes backup of a device was a perfect image. Take the backup, pull the SIM card, restore the backup to a new phone with the sim card installed, and it was like nothing had happened. No reauthentication. No missing notifications. No lost data. Ever. It was nice.

Security theatre killed this. Everyone must be assumed to be a moron incapable of living with the consequences of their own choices at all times.

Post by nkrisc » Mon, Feb 02, 2026, 2:13 PM UTC

CrispinS wrote: post #73

csmantle wrote: post #46

Methodology is one thing; I can't really agree that deploying an LLM to do sums is great. Almost as hilarious as asking "What's moon plus sun?" But phenomenon is another thing. Apple's numerical APIs are producing inconsistent results on a minority of devices. This is something worth Apple's attention.

> What's moon plus sun? Eclipse, obviously.

Post by embedding-shape » Mon, Feb 02, 2026, 2:15 PM UTC

dahcryn wrote: post #175

embedding-shape wrote: post #157

Earlier quoted context omitted.

Blog post dated 28 Jan 2026, the bug fix posted 29 Jan 2026, so I guess this story had a happy ending :) Still, sad state of affairs that it seems like Apple is still fixing bugs based on what blog posts gets the most attention on the internet, but I guess once they started that approach, it's hard to stop and go back to figuring out priorities on their own.

I think you overestimate the power of a blogpost and the speed of bugfixing at Apple for something like this. I almost guarantee there is no way they can read this blogpost, escalate it internally, get the appropriate approval to the work item, actually work on the fix, get it through QA and get it live in production in 3 days. That would only happen on really critical issues, and this is definitely not critical enou…

Post by pjmlp » Mon, Feb 02, 2026, 2:25 PM UTC

llm_nerd wrote: post #166

zozbot234 wrote: post #160

Earlier quoted context omitted.

So the underlying issue is that the iPhone 16 Pro SKU was misdetected as having Neural Accelerator (nax) support and this caused silently wrong results. Not a problem with the actual hardware.

Apple's documentation is utter garbage, but this code almost seems like a separate issue (and notably the MLX library uses loads of undocumented properties in metal which isn't cool). It looks like the change used to allow the NAX kernel to be used on the iPhone 17 or upcoming 18 if you're on 26.2 or later, to instead only allow it on the iPhone 17 Pro or upcoming 18. I'm fairly sure the GPU arch on the A19 is 17. Th…

Post by layer8 » Mon, Feb 02, 2026, 2:28 PM UTC

csmantle wrote: post #46

Methodology is one thing; I can't really agree that deploying an LLM to do sums is great. Almost as hilarious as asking "What's moon plus sun?" But phenomenon is another thing. Apple's numerical APIs are producing inconsistent results on a minority of devices. This is something worth Apple's attention.