IBM, Together AI Unveil $240M NVIDIA-Powered Inference Cluster on IBM Cloud

IBM and Together AI have launched a $240 million NVIDIA-powered inference cluster on IBM Cloud. The collaboration aims to deliver open-source model inference at scale for enterprises globally.

The large-scale inference cluster is built using NVIDIA HGX B300 systems, which can deliver up to 30 times more AI factory output compared to prior generations.

Together AI will use this cluster to provide better performance and token economics to enterprises as they look to efficiently scale their AI deployments.

'Enterprises want the performance of the best frontier models without the closed-model price tag, and that only works if the infrastructure underneath is fast and reliable at scale,' said Vipul Ved Prakash, CEO at Together AI.