Reading up on Mac Studio
5 deep · digging since apr 20
- Mac mini alternatives for local LLMs: M6, M5 and Strix Halo
For local LLMs, memory bandwidth and size determine token speed and model capacity; Strix Halo offers more memory per dollar, while Apple Macs with higher bandwidth generate tokens faster.
- Apple’s Mac Mini Went Viral. Why Can’t You Buy One Right Now? - WSJ
Apple's Mac Mini faces severe shortages and shipping delays of up to 12 weeks due to unexpected demand from AI power users running local large language models.
Takes
If you think at it, there are very little reasons to spend the same money for a Mac Studio M5 Ultra with 256GB of RAM if you can get, for the same price, 2x Macbook Pro with 128GB RAM and an RDMA cable. It is just a matter of developing good inference software. Do you agree?
@antirez
One of the coolest in person demos at #wwdc26 was @lmstudio running massive local models on 4 daisy chained Mac Studios with a total of 2tb memory Then they pulled out an iPhone and chatted with those models remotely over a secure connection I need to find a use for this
@stalman
Wanted to buy a new Mac Studio for San Francisco. We don’t even know how to make these anymore.
@steipete