Is DeepSeek v4 (Flash) really extremely cheap to run? If yes, how?

Hi. I don't have a GPU. So my biggest "local LLM" experience has been running ~26B models with single-digits tps values. However, the "serving economy" of DSv4 models look like a riddle to me. The Flash model has 284B parameters, but providers (e.g. OpenRouter) charge so little for it it's ridiculo

中文全文翻译正在补齐，可先查看下方英文原文。

Hi. I don't have a GPU. So my biggest "local LLM" experience has been running ~26B models with single-digits tps values. However, the "serving economy" of DSv4 models look like a riddle to me. The Flash model has 284B parameters, but providers (e.g. OpenRouter) charge so little for it it's ridiculo