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

6 hours ago

Hacker News

The break-even

How you’d use it

Mostly for

Tokens a day

Context window you want

Custom input to output ratio

Assumptions you can change

Electricity, $/kWh API speed, tok/s

Assume API prices keep falling How fast they fall

Where nothing has been measured, local speed is estimated as memory bandwidth ÷ bytes read per token × , and labelled as such. API speed only affects the time comparison.

How this is calculated

The small print that isn't small

You finished the article!

Want to go deeper or explore more stories?

Full Article on Hacker News More Tech News

Reading Mode

Adjust typography and theme to your preference.

Typography

Text Scale

View Original

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

The break-even

How you’d use it

The small print that isn't small

Reading Mode

Related Stories

Linux from Scratch

Show HN: Macros with a Behringer FCB1010 MIDI Pedalboard in macOS

Charts built for Chat

Amazon vs. Perplexity – U.S. Court of Appeals for the Ninth Circuit

A Beginning for Mathematics

Related Stories