News for hackers. Stuff that matters.
Re:Mesh LLM: distributed AI computing on iroh by wlesieutre on Saturday July 11, 2026 @09:37PM (#48877510)
Equivalent M3 machines no longer for sale from Apple (only up to 96 GB) but can be had on eBay for around $14,000 each
Re:Mesh LLM: distributed AI computing on iroh by drawnwren on Sunday July 12, 2026 @02:29AM (#48878855)
It's notable that they're so valuable because they feature 800Gbps of memory bandwidth. About twice what's available on the top end of M5, and exactly what makes llm inference fast.
Re:Mesh LLM: distributed AI computing on iroh by embedding-shape on Sunday July 12, 2026 @05:17AM (#48879620)
> because they feature 800Gbps of memory bandwidth. About twice what's available on the top end of M5

Ouch, about half of the memory bandwidth of a dedicated GPU though :/ Running LLMs on Apple hardware still doesn't make any sense to me.

Re:Mesh LLM: distributed AI computing on iroh by khalic on Sunday July 12, 2026 @05:20AM (#48879643)
M5 max has 614GB/s, you mean the m4?
Re:Mesh LLM: distributed AI computing on iroh by drawnwren on Sunday July 12, 2026 @02:13PM (#48883159)
Oh, I was looking at every M5 except for the 40-core M5 Max. They have 460.