Hacker News new | ask | show | jobs
by znnajdla 51 days ago
I’m beginning to challenge the assumption that datacenters are more efficient. I can get the same computing power out of a single Mac Mini 32 GB that I get from from an AWS virtual machine that costs hundreds of dollars per month. Even compared to cheap baremetal providers like Hetzner, the Mac Mini pays for itself in a few months of cloud costs. How exactly are datacenters more efficient? I don’t see it in the price. It may be the costs of centralizing large amounts of compute actually make it more expensive, not less, when accounting for profit margins, and considering the fact that base infrastructure (power, internet) is a given in every home anyway.

There are huge hidden costs in datacenter prices that are simply unnecessary for most casual users of compute. Salaries of staff to maintain datacenters, redundancy and high availability of nine 9s that are simply not required by most customers, as well as real estate costs are all non-existent costs in a homelab setup because those are living costs you pay for anyway, with or without a home server.
1 comments
gruez 51 days ago
>I can get the same computing power out of a single Mac Mini 32 GB that I get from from an AWS virtual machine that costs hundreds of dollars per month.

This quickly breaks down when you're talking about large models that needs terabytes of memory to run[1]. There's no way that you're going to be able to amortize that for a single person.

[1] https://apxml.com/models/glm-51

link
ipaddr 51 days ago
The comment is about smaller models
link
gruez 51 days ago
Right, but what are you going to do with small models? If your time is worth anything at all you'd pay for the $100 claude code/codex pro subscription, rather than fumbling around with the models quantized enough to fit on your mac.
link
mhitza 51 days ago
If you're building agentic processes (harnesses) for business processes local models are a great way to do that, while keeping your data, and any personal data, private.

If you're vibe coding a codex/claude subscription makes more sense as a more polished experience.

I don't vibe code, but I use self hosted models with codex for code review and snippet generation.

link
ret32f 51 days ago
If small models keep improving for specific purposes and larger models have diminishing returns, then what?

E.g. I can see a world where you have a local model that is specialised just for producing code.

link
20after4 50 days ago
$100 isn't going to buy you much access to claude code when they start charging a profitable fee for using it.
link