Blog Network

Sam Witteveen · 2026-10-30 · notable

Sam Witteveen — '3,000 Tokens/Sec Locally: Testing the ZGX Fury'

Sam Witteveen tests HP's ZGX Fury, a shared desktop AI machine built on NVIDIA's GB300 chip with 748 GB of memory, and shows local inference speeds, software and use cases.

Sam Witteveen video thumbnail for testing the HP ZGX Fury local AI machine

Sam Witteveen benchmarks HP's ZGX Fury, a compact GB300 machine a whole team can share for local AI.

What is it?

'3,000 Tokens/Sec Locally: Testing the ZGX Fury' went up on Sam Witteveen's channel on 30 October 2026. The video reviews HP's ZGX Fury, a larger sibling of the ZGX Nano (DGX Spark) built on NVIDIA's GB300 chipset with 748 GB of memory.

How does it work?

The video explains how the machine's memory works, then covers HP's ZGX Runtime and Z Toolkit software and its Red Hat certification. It follows with benchmarks and use cases such as running agentic systems and on-prem AI.

Why does it matter?

Teams that cannot send data to a cloud API need local hardware big enough for large models. A shared machine with this much memory is one option, and the video shows what speed it reaches.

Who is it for?

teams planning on-prem AI

Sources

Tags

  • video
  • sam-witteveen
  • hp
  • zgx-fury
  • nvidia
  • gb300
  • local-ai
  • hardware
  • inference

← All releases