$16,000 Quad AI Geekom mini PC cluster gets DeepSeek V4 Flash treatment with 512GB RAM — reaches 14.61 tokens per second

Source: TechRadar· Efosa Udinmwen· August 21, 2026
$16,000 Quad AI Geekom mini PC cluster gets DeepSeek V4 Flash treatment with 512GB RAM — reaches 14.61 tokens per second
SynaBot summary

A company has connected four mini PCs to create a local AI cluster capable of running a large language model. This setup achieved a processing speed of 14.61 tokens per second, demonstrating a viable alternative to cloud-based AI.

Key takeaways

  • Four mini PCs linked via USB4 for local AI processing
  • AMD Ryzen AI Max+ 395 processors power the cluster
  • Total memory reaches 512GB for enhanced AI performance
  • Local LLM execution offers cloud-free AI solutions

Why it matters

This development offers a glimpse into more accessible, on-premises AI processing for businesses. It suggests that powerful AI tasks might soon be handled locally, potentially reducing costs and enhancing data security for users of AI tools.

This story was reported by TechRadar. Read the full original article:
Read on TechRadar

Try this on SynaBot

Related AI assistants, prompts, and tools from the SynaBot catalog.

More in Enterprise & Adoption

View all