DeepSeek reports 155T tokens/day from one cluster with 96% input cache hits
Overview
DeepSeek reports that one of its GPU clusters processes 155 trillion tokens per day, at $38 revenue per GPU-hour, according to a Latent Space post quoted by X user swyx.
The figures are cited in a post about GPU value and stock market effects, and the report does not include the 96% input cache hit rate named in the headline or any further detail on how the figures were measured.
swyx's own post, a joke that every GPU sold today gained about 30% in lifetime value and would lift the stock market about $600B, relies on those cluster figures only as background.
Written by AI from the articles below · updated Oct 21, 3:22 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
swyx@swyxXswyx says GPU value gains could lift the stock market by $600BAIswyx says every GPU sold today gained about 30% in lifetime value, so the stock market should rise about $600B. The post is a joke about GPU demand and its effect on stocks. Quoted context from Latent Space says DeepSeek's cluster handles 155T tokens per day at $38 revenue per GPU-hour.

Heat Trend
Not enough continuous observations to show a trend yet.