HIVE’s GPU-cloud subsidiary BUZZ plans 2,016 NVIDIA Blackwell Ultra GPUs in GB300 NVL72 systems for Merritt, British Columbia.

HIVE’s Form 10-Q describes a dedicated cluster comprising 2,016 NVIDIA Blackwell Ultra GPUs housed in NVIDIA GB300 NVL72 rack-scale systems. The 2,016 figure counts GPUs, not servers or racks.

The planned deployment is at a facility in Merritt, British Columbia, and is intended to support large-scale AI training, inference and advanced enterprise workloads. HIVE expects deployment during the first quarter of calendar 2027; the filing does not present the cluster as already operational.

HIVE estimates approximately $185 million in deployment-related capital expenditures, including the accelerated computing cluster, associated hardware and service warranties. This deployment estimate is separately stated from the $186.9 million equipment-and-services purchase agreement and should retain its own scope.