It's 100,000 GPUs, not NVL72 racks: viral cluster-size claim corrected
firstadopter · x · 2026-09-07
firstadopter corrects a viral claim about massive training clusters: the real figure is 100,000 GPUs, not 100,000 NVL72 servers (which would imply 7.2 million Blackwell GPUs). He notes million-GPU/TPU training clusters remain in the future, and the widely shared estimate was off by roughly an order of magnitude.
Related event: Correction: Rumored Giant Cluster Is 100K GPUs, Not 100K NVL72 Racks(2 posts)→
More from Infra
- OpenRouter crosses 400T monthly inference tokens, up ~27x in a year — gajesh · 2026-09-07
- Goldman Sachs sees nearly 80% upside for Kospi at 12,000 target on AI memory boom — Polymarket · 2026-09-07
- How compute-efficient is Astra? Estimates suggest 10x gap vs smaller labs — teortaxesTex · 2026-09-07
- Run Qwen3 27B Free on Kaggle: ~20 Hours of GPU Usage You Can Point Hermes At — TheMoonMidas · 2026-09-07
- Tuning draft acceptance for Qwen3.6-35B MTP speculative decoding in llama.cpp — Bulky-Priority6824 · 2026-09-07
- Google's MaxKernel: Multi-Agent System Writes TPU Kernels at Expert Level — google · 2026-09-07