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

You’re not wrong that Apple’s memory prices are unpleasant, but also consider the competition - in this context (running LLMs locally) laptops with large amounts of fast memory that can be purposed for the GPU. This limits you to Apple or one specific AMD processor at present.

An HP Zbook with an AMD 395+ and 128Gb of memory apparently lists for $4049 [0]

An ASUS ROG Flow z13 with the same spec sells for $2799 [1] - so cheaper than Apple, but still a high price for a laptop.

[0] https://hothardware.com/reviews/hp-zbook-ultra-g1a-128gb-rev...

[1] https://www.hidevolution.com/asus-rog-flow-z13-gz302ea-xs99-...



Yeah, I'm by no means saying that Apple is uniquely bad here -- it's just an issue I've been frustrated by since the first M1 chip, long before local LLMs made it a serious issue. More memory is always a good idea, and too much is never enough.


You can get any low spec laptop that has no soldered DIMMs and just replace them with the maximum supported capacity.

You don't necessarily need to go the maxed up SKU.


Would that be unified memory? Where the gpu and cpu can share the memory? Which is key for performance.


Right, no, it wouldn't, I appreciate that in this particular context my comment was entirely wrong.

Thanks for helping me see it!


No, it wouldn’t. You’d be limited to using the CPU and the lower bandwidth system memory.


The framework desktop will get you the 395+ and 128gb of ram for 2k USD.




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

Search: