Read this but think of Mac GPU universal memory running LLM(apple.com)
apple.com
Read this but think of Mac GPU universal memory running LLM
https://www.apple.com/hk/en/newsroom/2025/10/apple-unleashes-m5-the-next-big-leap-in-ai-performance-for-apple-silicon/
3 comments
> Just who is going to be the os or llm provider(s) in the new era I wonder.
We've already seen that question answered. TSMC has two customers for cutting edge nodes; Apple and Nvidia. Apple refuses to address the datacenter market, so they're missing out on the trillions of dollars to be made in high-margin compute.
Keep in mind, Apple could just drop their pride and support Nvidia drivers again. macOS can run CUDA if Apple just signs the installer, they could be selling rackmount Macs as high-performance ARM clusters. But nope! Apple insists on losing.
We've already seen that question answered. TSMC has two customers for cutting edge nodes; Apple and Nvidia. Apple refuses to address the datacenter market, so they're missing out on the trillions of dollars to be made in high-margin compute.
Keep in mind, Apple could just drop their pride and support Nvidia drivers again. macOS can run CUDA if Apple just signs the installer, they could be selling rackmount Macs as high-performance ARM clusters. But nope! Apple insists on losing.
Dupe (1243 points, 3 days ago, 1372 comments) https://news.ycombinator.com/item?id=45591799
Now is like IBM mainframe vs apple mac/microsoft DOS/mac/windows time. Nvidia era is peaking and we are going back.
Just who is going to be the os or llm provider(s) in the new era I wonder.
As in the past we are seeing the chasm. One has to remember there are two different market type. The infra and the app.
Not THINK … but “Think Different” …