Show HN: Sunk Cost – How long until a local LLM rig pays for itself? • Hacker News Board

Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#1

Post by rlindsey123 » Tue, Sep 15, 2026, 1:37 AM UTC

I kept hearing "just buy a Mac and run models locally, it pays for itself" and wanted to check. Sunk Cost takes a machine, a model and how many tokens you use a day, and works out how long the hardware takes to pay back against renting the same model by the token.

Obviously there are other reasons to buy your own hardware aside from just saving money on llms but this is just looking at it from a raw cost saving perspective.

If you have any ideas on how I can make this more helpful lmk!

Show HN: Sunk Cost – How long until a local LLM rig pays for itself?
sunkcost.ai

Re: Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#2

Post by hyperhello » Tue, Sep 15, 2026, 2:33 AM UTC

I doubt it will ever be cost effective for the foreseeable future. The AI companies have astonishing amounts of compute and they’re effectively dumping it on the market.

Re: Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#3

Post by jrflo » Tue, Sep 15, 2026, 2:33 AM UTC

43 years to break even on Qwen 3.8 at 25% the speed of the API, lol. I like the idea of local models for really small tasks like automation/toolcalling, but it will probably never make sense for coding. I tried them and it was just excruciating compared to what you get for $100 a month from a subscription.

Re: Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#4

Post by itake » Tue, Sep 15, 2026, 2:33 AM UTC

I have a home server running vibed applications. VPS host would cost $25/mo or $300/yr.

Mac mini can also build iOS applications. I think if you’re a mobile dev, you can have concurrent builds for your agents instead of everyone waiting on a single machine to finish.

Re: Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#5

Post by ProjectArcturis » Tue, Sep 15, 2026, 2:37 AM UTC

Local LLMs are not really about saving money, they're about autonomy. Choose the exact model you want, fine-tune it if you want, and no one can take it away from you.

Re: Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#6

Post by poincareball » Tue, Sep 15, 2026, 2:37 AM UTC

[dead]

Re: Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#7

Post by mcone » Tue, Sep 15, 2026, 2:38 AM UTC

The idea that you need a new machine is pretty ridiculous. I bought a used HP Omen with a 3090 last month for $2k. 57t/s with Qwen 3.8.

Re: Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#8

Post by txrx0000 » Tue, Sep 15, 2026, 2:39 AM UTC

It pays off instantly, because OpenAI/Anthropic can no longer see what I'm doing and that's worth a lot of money to me. If I am offloading some of my thought processes to a machine, I want to own that machine. And if I finetune the model, I can gain access to parts of thought space that are cordoned off by OpenAI/Anthropic/Alibaba/whomever due to their "alignment" efforts (i.e. alignment to the AI company rather than me). Otherwise, it's like if someone else owns a part of my mind and has a backdoor into my mind.

Re: Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#9

Post by gruez » Tue, Sep 15, 2026, 2:42 AM UTC

hyperhello wrote: post #2

I doubt it will ever be cost effective for the foreseeable future. The AI companies have astonishing amounts of compute and they’re effectively dumping it on the market.

"If they are selling it for less than it cost to make, buy as much as you can."

-- Warren Buffett

Re: Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

#10

Post by shadowpho » Tue, Sep 15, 2026, 2:42 AM UTC

I like this calculator but it’s really wrong at least for dgx spark. I have one and I get 4x the tokens/s .