Massive RL Run: ~1,000 GB300 GPUs and $5M?

natolambert · x · 2026-07-16

This reply discussed the potential scale of a post-training RL run, with the author providing a rough estimate: around 1K GB300 GPUs, running for 1 week, and costing roughly $5 million.

They added that while this estimate is an intuitive guess based on Claude—and they would welcome a more rigorous mathematical analysis—Claude's intuition regarding inference costs might not be entirely reliable in agentic settings.

Original post →

More from Infra

Infra channel →