News
SovereignDeutsche Telekom boosts its sovereign AI push with 100 million for MistralInferenceAMD Completes Taalas Acquisition to Strengthen AI Inference PortfolioSovereignIndia’s Sarvam AI launches GPU service for open modelsClustersNew UB North Campus structure to house AI supercomputer system for research usesClustersIntroducing Together Storage Accelerator: fast, free data caching for your GPU clusterNeocloudsJensen Huang’s Charity Committed $350 Million to CoreWeaveClustersOak Ridge's AI Factory Moment: Lux, Nuclear Power, and the Next Data Center FrontierDealsNscale’s ByteDance GPU deal draws scrutiny over US chip curbsDealsNscale’s ByteDance Deal Faces Scrutiny Under US Chip CurbsSovereignNexusIgnite Plans Sovereign AI Cloud in Jordan, Starting With Its UniversitiesSovereignDeutsche Telekom boosts its sovereign AI push with 100 million for MistralInferenceAMD Completes Taalas Acquisition to Strengthen AI Inference PortfolioSovereignIndia’s Sarvam AI launches GPU service for open modelsClustersNew UB North Campus structure to house AI supercomputer system for research usesClustersIntroducing Together Storage Accelerator: fast, free data caching for your GPU clusterNeocloudsJensen Huang’s Charity Committed $350 Million to CoreWeaveClustersOak Ridge's AI Factory Moment: Lux, Nuclear Power, and the Next Data Center FrontierDealsNscale’s ByteDance GPU deal draws scrutiny over US chip curbsDealsNscale’s ByteDance Deal Faces Scrutiny Under US Chip CurbsSovereignNexusIgnite Plans Sovereign AI Cloud in Jordan, Starting With Its Universities
EveryNeocloud

Nvidia Blackwell

B200, GB200 NVL72, B300 and GB300. 35 providers on EveryNeocloud so far.

Blackwell is Nvidia's generation of data centre GPUs announced in March 2024, after Hopper. It includes the B200 GPU, the GB200 superchip that pairs two B200s with a Grace CPU, and the Blackwell Ultra parts B300 and GB300 of 2025. Its best-known product is the GB200 NVL72, a liquid-cooled rack in which 72 GPUs act as one large GPU.

What is new

A Blackwell GPU joins two large dies into one chip with 208 billion transistors, made by TSMC. It adds support for 4-bit numbers (FP4), which roughly doubles inference throughput over 8-bit for models that tolerate it. In the NVL72 rack, fifth-generation NVLink connects all 72 GPUs at very high bandwidth, so a model can spread across the rack as if it were one machine. A rack draws over 100 kW, so it needs liquid cooling.

Who runs it

CoreWeave was first to offer GB200 NVL72 widely in early 2025. Microsoft's Fairwater sites, Oracle's Stargate campus at Abilene, xAI's Colossus 2, Nscale, Nebius and IREN all run Blackwell at large scale, and sovereign builds in Malaysia, Korea and the Gulf use it too. Nvidia's next generation, Rubin, is due from 2026, so providers buying Blackwell now must plan for fast obsolescence.

Famous nvidia Blackwell providers

Further reading

Photo credits on this page

The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

The weekly digest

Every Monday: the provider of the day, new pages on EveryNeocloud, and the conferences and anniversaries of the week ahead.