Model-as-a-Service on zCLOUD delivers open-weight and open-source models such as Kimi, GLM, Llama, GPT-OSS, Gemma, and Qwen on Zettabyte’s GPUs through a single API. zCLOUD offers access to NVIDIA H100, H200, B200 and B300 GPUs and provides three fully managed ways to access capacity, backed by a 99.5 percent uptime SLA target. Dr. David Ku, Technology Leader at Zettabyte, stated, “AI computing will be everywhere, from hyperscale data centers to the edge. The supporting AI infrastructure and software must be compatible, resilient, and agile.” Model-as-a-Service on zCLOUD is available at www.zettabytecloud.com.
