Google Cloud is adding NVIDIA's Blackwell GPUs, specifically the RTX Pro 6000 model, to its offerings.

Using NVIDIA's NBFP4 precision format for model checkpoints provides optimal performance when combined with TensorRT LLM optimizations.

NVIDIA's TensorRT LLM is an open-source SDK that can optimize inference performance on NVIDIA hardware with only a few lines of code.

The NVIDIA RTX Pro 6000 GPU features 96 gigabytes of VRAM, which enables the deployment of multiple models on a single GPU.

NVIDIA's Vera Rubin hardware is expected to be available on Google Cloud in the latter half of the current year.

NVIDIA's TensorRT LLM provided day-zero support for Google's Gemma 4 model.

Google Cloud will be one of the cloud providers to offer NVIDIA's next-generation Vera Rubin hardware for inference and training.