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

原始链接: https://sunkcost.ai/

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.

相关文章

原文