GEEKOM Demonstrates Four-Node Mini PC AI Cluster with Local DeepSeek Model

GEEKOM has demonstrated a four-node AI cluster built from its compact A9 Mega Mini PCs, showing how small-form-factor systems can be combined for local enterprise AI applications.

The cluster connects four A9 Mega units via USB4, allowing them to operate as a distributed platform without requiring a traditional server rack or proprietary high-speed networking equipment. Each system is powered by AMD’s Ryzen AI Max+ 395 processor, featuring 16 Zen 5 CPU cores, Radeon 8060S graphics and unified memory.

Running Ubuntu, ROCm and DwarfStar software, the cluster distributes the DeepSeek V4 Flash model across all four machines. It also provides an OpenAI-compatible API, enabling integration with applications, AI agents and automation tools.

A key advantage of the setup is local processing. Businesses can analyse documents, source code, contracts and internal knowledge without sending sensitive information to a public cloud. GEEKOM says the system has also been tested with context windows of up to 250,000 tokens, making it suitable for lengthy documents and complex workflows.

According to the company, the cluster achieved approximately 14.61 tokens per second at single concurrency, with a 95th-percentile time to first token of around 0.42 seconds in its 32- and 128-token tests. Organisations can begin with one or two A9 Mega systems and expand to four as their requirements grow.

The demonstration highlights the potential of compact PCs as scalable local AI platforms for businesses, laboratories, classrooms and edge-computing environments.

Source: GEEKOM via PR Newswire. Performance figures and capabilities are based on company-reported testing.