NVIDIA Vera Rubin NVL72 deployments online
Company: CoreWeave
The claim, verbatim
CoreWeave brought online multi-rack NVIDIA Vera Rubin NVL72 deployments, with Cognition's first production workloads achieving 4.8x token throughput versus GB200 NVL72.
Source (primary)
coreweave 8-K exhibit (coreweave3q26earningspress.htm) (SEC EDGAR (8-K Ex), press_release)
View cached copy (2026-11-11)Live source ↗
Quote: “Brought online multi-rack NVIDIA Vera Rubin NVL72 deployments, with the first production workloads for Cognition on the platform achieving 4.8x greater token throughput than GB200 NVL72”
How we checked this
This claim has not yet been checked assertion-by-assertion against its source. It carries a cited source and quote, but the deeper check has not run. When it does, the result appears here whatever it says.
Additional evidence
confirms coreweave 8-K exhibit (coreweave3q26earningspress.htm)
Quote: “Brought online multi-rack NVIDIA Vera Rubin NVL72 deployments, with the first production workloads for Cognition on the platform achieving 4.8x greater token throughput than GB200 NVL72”