Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> Apple’s most powerful Mac raises the bar for local AI

Wow, "Local AI" mentioned in the subheading above the fold - it's really awesome to see Apple leaning into this use case and I think it will definitely pay off for them going forward. Fingers crossed Apple is able to put some engineering effort towards shipping with one of the frontier open weight models included and optimized exactly for the machine.



I am absolutely open to being corrected but I can't think of a single current era FOSS project that apple is optimizing and shipping with their computers.


Shipping with their computers -- maybe not, but they did make FoundationDB open source (again) and are developing and maintaining it.


The local ai is used by Apple services, mostly. Though there is a Swift SDK to access it, apparently.


You can run Ollama and it’s kind with MLX models for speed.

Tend to be better than Apple AI.


The product marketing managers write for the target audience; of course they know lots of people buying these are the local LLM crowd.

I actually wouldn't want a serious model shipping 'on disk'. Models release so often, it's going to get outdated quickly. LMStudio is trivial to set up.


Now imagine a model shipped in silicon that gives 5,000 tokens per second at Opus 4.8 quality


U2-OSS-vBono-120b




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: