With NVIDIA RTX PRO 6000 Pro GPUs on Cloud Run, deploying massive models is easy: no reservations, no cluster management — just code.

Google Cloud Platform provides a suite of cloud computing services for building, deploying, and managing applications and infrastructure on Google's global network. Developers can learn about cloud-native development, machine learning, and big data analytics to leverage GCP's scalable and reliable cloud infrastructure for their projects.

Google Cloud

Google Cloud Run now supports NVIDIA RTX PRO 6000 Blackwell GPUs in preview, enabling serverless deployment of large AI models (up to 70B+ parameters) without cluster management or reservations. The GPU offers 96GB vGPU memory, 1.6 TB/s bandwidth, and FP4/FP6 precision support, with instances scaling from zero to ready in under 5 seconds. Available on-demand in select regions (us-central1, europe-west4, with limited availability in Asia), Cloud Run handles driver installation automatically and supports up to 44 vCPU and 176GB RAM per instance. Use cases include real-time generative AI inference, model fine-tuning via Cloud Run jobs, and custom scaling with worker pools.

Cloud Run supports NVIDIA RTX 6000 Pro GPUs for AI workloads