Acrab Introduces GELIX 1 SoC and Agent Box for Local AI Applications
Acrab announced in a press release the launch of its GELIX 1 System on Chip and Agent Box platform for local AI processing. The GELIX 1 chip, built on a 5 nanometer process, is engineered to run models with up to 100 billion parameters through a comprehensive software stack for private and responsive AI agents operating at the edge.
The GELIX 1 features a 20 core Arm CPU, a multicore NPU accelerator, and unified memory bandwidth reaching 273 GB per second. It is designed to support high performance, memory intensive inference workloads without dependence on cloud connectivity.
Acrab’s Agent Box builds on this chip to provide a personal edge AI hub capable of local large model inference, multimodal interactions, persistent memory, and agent orchestration. The company plans to collaborate with device manufacturers and developers to integrate its platform into products such as AI network attached storage systems, AI PCs, smart vehicles, and industrial or service robots.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.
Also, consider following us on social media:
More from Data Centers
Sep 17 Teledyne LeCroy Releases PCIe 7.0 Protocol Exerciser Sep 17 XKL Adds Low Latency Optical Links for Distributed AI Sep 17 Sentry AI deploys 100th SolarGuard security trailer Sep 17 Terragrit Secures Investment From National Grid Partners Sep 17 FirstLight Fiber Signs Hyperscaler for 240 Mile Albany to Boston RouteSilicon Brief
Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.
Industry analysis
2025 Global Business Services Agenda: Gen AI Takes Center Stage
This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.
Read moreYou may also like
BrainChip Launches AKD1500 PCIe Card for Edge AI Testing
SDMC Showcases Deployable AI Home Architecture at IBC 2026
ASUS Expands AI Infrastructure From Cloud to Edge
Acer Shows Compact RTX Spark Desktop Design at IFA 2026
Abacus.AI Releases Three Smaug Open Weight Models
Daily AI Brief: the AI news that matters, in your inbox.