DGX Spark buyers weigh OS support before local LLM use

Two DGX Spark machines are being considered for office work centered on , or LLMs. The intended use is inference only, meaning existing models would be run to produce answers, with no fine-tuning planned.

A workstation drawing more than 700 watts would be hard to tolerate in an office because of heat and power use, so a smaller machine is being evaluated. The main concern is the support lifetime of the DGX Spark , which is based on Ubuntu 24.04.

If Nvidia stopped supporting the device around 2028 and pushed buyers toward a newer product, spending about 13,000 euros on two units would be harder to justify. The of 273GB/s is seen as a weakness, but keeping the room comfortable matters more than getting the highest compute performance for the price.

Key points

  • Two DGX Spark units are being considered for office-based .
  • The goal is to run existing models, not to fine-tune them.
  • A 700W-plus workstation may create too much heat and power demand for an office.
  • Ubuntu 24.04 support lifetime matters because it affects how long the device can safely be used.
  • The 273GB/s is a tradeoff, but room temperature is a bigger concern here.
Read original