Hacker News

Favorites Setup
Comment by N_Lens | original | Benchmarking Pocket-Scale Inference
[−]N_Lens · 2026-08-30 Sun 07:00 UTC · link
Apple has been stingy with RAM in consumer hardware. RAM prices will continue escalating, some analysts say into 2030, and this will make it more difficult to build next generation phones with sufficient memory for meaningful ML workloads.

I hope there's some kind of inversion in the current chip economics, because I love distributed/democratized/private compute, but currently cloud based LLM inference seems to be much more viable. I don't see local llms meaningfully viable for the general usecase in the near future.

[−]bb123 · 2026-08-30 Sun 12:06 UTC · link
I'm not sure about that. I can run Qwen 3.8 27B at acceptable speed on an M1 MacBook Pro from 5 years ago. Thats Opus 4.6 Quality, on 5 year old consumer hardware. I think the trend is the opposite - smaller models that can run on hardware people already have are getting better and better.
[−]sidpatil · 2026-08-30 Sun 16:09 UTC · link
How much RAM does your system have?
[−]cousinbryce · 2026-08-30 Sun 14:17 UTC · link
There’s something I’d don’t understand about this. Apple’s RAM is on their own die. Is the price of RAM an indicator for the cost of die space in general?
[−]dgacmu · 2026-08-30 Sun 14:49 UTC · link
No - DRAM is made on a different process than compute. Apple uses dram made by the usual dram manufacturers.

The dram shortage is a combination of high demand + shifting manufacturing to HBM, which consumes more wafer capacity than DDR5