Patel: DeepSeek inference requires 160 GPUs and $10 million per replica
Dylan Patel · No Priors Ep. 127 | With SemiAnalysis Founder and CEO Dylan Patel · Aug 14, 2025 · at 5:48
Dylan Patel (SemiAnalysis) breaks down the massive hardware scale and orchestration required to serve advanced reasoning models like DeepSeek.
0:00 / 0:09exact quote · 9.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Like the DeepSeq implementation of inference is like a 160 GPUs or something like that, like that's over ten million dollars of Hardware. And then that's just one replica.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Dylan Patel
Patel: Anthropic has surpassed OpenAI in API revenue
“Anthropic has eclipsed OpenAI and API revenue, and their API revenue is primarily not thinking. It's clawed for, but it's not in the thinking mode.”
Patel: Hyperscalers cannot replicate CPU and storage profit margins in GPUs
“Their ROIC is, like, extremely high on CPU and storage, and to assume that it can, like, translate over to GPUs is, is a bit of a fallacy, which is why a lot of these companies are moving in, right?”
Patel: Microsoft's AI hardware programs fail because Microsoft lacks model understanding
“There's a reason why Microsoft's hardware programs suck, right? Because they don't understand models at all.”
Patel: AMD cannot catch NVIDIA due to poor software, networking, and co-design
“Why is AMD not catching up despite being awesome at hardware engineering? Well, yeah, they're bad at networking, but also they suck at software and they can't do hardware software co-design.”