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,...

GMKtec is recognized as a PayPal Star Merchant for its global e-commerce growth, as the AI PC brand expands desktop AI computing into international markets.

Berlin, Germany — September 2026 — GMKtec, a global provider of compact computing solutions, will showcase its latest generation of Mini PCs and AI-ready computing platforms at IFA 2026 in Berlin, highlighting its vision for making powerful local AI computing more accessible to consumers and businesses worldwide. Visit GMKtec at Hall 5.2, Booth 455,...

Have your AI bills spiraled out of control? If running cloud-based tools like OpenAI has left you with shocking daily costs, you’re not alone. As AI adoption accelerates, so do the expenses—and the dependency on cloud infrastructure.GMKtec is changing that. Introducing the EVO-T2 Series, the second-generation desktop AI supercomputing center, engineered to bring massive...