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

journal.rafaelcosta.me

262 points by rafaelcosta 11 hours ago


csmantle - 8 hours ago

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.

DustinEchoes - 8 hours ago

I wish he would have tried on a different iPhone 16 Pro Max to see if the defect was specific to that individual device.

raincole - 9 hours ago

Low level numerical operation optimizations are often not reproduceable. For example: https://www.intel.com/content/dam/develop/external/us/en/doc... (2013)

But it's still surprising that that LLM doesn't work on iPhone 16 at all. After all LLMs are known for their tolerance to quantization.