logoalt Hacker News

delusionalyesterday at 5:52 PM5 repliesview on HN

What are your use-cases for 128gb of RAM? I find it hard to imagine what you could be doing with that, so it must be interesting :)


Replies

macNchzyesterday at 6:32 PM

I'm not the person you're replying to, but I do have a 64GB machine that I'd been planning to bump up to 128 right around the time the prices went through the roof. My uses are:

- VMs, I'm leaning on them more and more for sandboxing stuff I'm working on, both because of the rise in software supply chain threats, and to put guardrails around AI agents.

- Local LLMs experimentation, even pretty big MoE models (GPT OSS 120b) run pretty usably (~10 tokens/sec) with the latest tooling on a 16GB GPU and a lot of system memory.

- Even compared to a fast NvME drive, it's super nice to load a big dataset into memory and just process it right there, compared to working off of the disk.

grogenautyesterday at 7:01 PM

Unreal + blender + ide.

Fusion + blender + slicers.

Virt machines / docker + dev env

iOS Android web development

16 copies of Claude code, cursor or kiro

Any of that while running arc raiders and watching twitch or YouTube or plex

My gaming PC is usually at 50-70 gb use

My mbp for work is often at 90 and starting to swap.

My personal mbp is only 48gb and often swapping

I have 128 in everything except my smaller mbp personal.

show 1 reply
pxmpxmtoday at 12:28 AM

Unclear for a laptop, but for a workstation 1tb+ is what you want for any sort data science stuff.

show 1 reply
dzongayesterday at 7:26 PM

most people who are into graphics processing e.g video-games, 3d for films/entertainment industry etc need these "PRO-workstation" machines, or doing fluid mechanics

if your work is around data | software engineering (web backends etc) like me - a MacBook Air tends to be sufficient

0x457yesterday at 7:01 PM

Running FatLTO on Chrome.