HP launches palm-sized ZGX Nano AI supercomputer with NVIDIA GB10
hp launched the zgx nano, a 15x15cm ai supercomputer powered by the nvidia gb10 grace blackwell superchip. it features 128gb unified memory and 1,000 tops fp4 performance, running local llms up to 200b parameters single-unit or 405b parameters when linked. jerome gabryszewski discussed the device ahead of the ai & big data expo, emphasizing the shift to local compute to handle autonomous ai lifecycles without cloud queues.
HP unveiled the ZGX Nano, a compact AI supercomputer measuring 15x15cm and powered by the NVIDIA GB10 Grace Blackwell Superchip. The device delivers 1,000 TOPS of FP4 AI performance with 128GB of unified memory, enabling local execution of Large Language Models (LLMs) up to 200 billion parameters on a single unit. By connecting two units via high-speed interconnect, users can scale to models with 405 billion parameters entirely on-premise. The system comes pre-configured with the NVIDIA DGX software stack and HP ZGX Toolkit.
In an interview ahead of the AI & Big Data Expo, Jerome Gabryszewski, AI & Data Science Business Development Manager at HP, highlighted the necessity of robust local hardware like the ZBook Ultra and Z2 Mini for iterative development. He also addressed enterprise data challenges, noting that organizations often underestimate the governance and architectural debt required to reconcile fragmented data ownership before automation can succeed.