News

If you’ve been following the world of local LLM inference, you may have heard a common criticism of AMD’s Strix Halo platform: with 256 GB/s of memory bandwidth, it can run large language models, but don’t expect spectacular speeds There’s some truth to that—but only half the story. Hardware sets the limits. Software determines...

A 10× improvement in prefill speed and a 1.85× boost in decoding performance bring large-scale local AI inference to a new level. As AI models continue to scale into the hundreds of billions of parameters, running them efficiently on a desktop system remains a significant challenge. Large models demand substantial memory capacity, high bandwidth,...

Following its global debut at IFA 2026 and worldwide launch on September 28, GMKtec's flagship EVO-X5 Pro expands into commercial AI with enterprise management, scalable multi-node computing, and offline 320B AI. SHENZHEN, China — October 9, 2026 — GMKtec today introduced the next stage of its EVO-X5 Pro desktop AI supercomputer at its China...

Measure your mini PC at the socket, define what your reading includes, and calculate daily energy use with a clear worked example.

A new generation of Agentic PC built for large-scale local AI computing AI is moving beyond simply running applications. The next generation of computing is increasingly about understanding context, reasoning across information, generating content, and taking action. This is the vision behind the Agentic PC. Today, GMKtec officially introduces the EVO-X5 Pro, a flagship...