HyPAIC: Personal AI Computer with High Bandwidth Flash for High Performance Trillion-Parameter LLM Inference

arXiv:2611.04144v1 Announce Type: new Abstract: LLMs have rapidly expanded from simple chatbots to agentic AI, where models directly use tools to solve complex problems. To improve problem solving, most frontier LLMs adopt an MoE architecture, pushing model sizes into the trillion-parameter regime. While cloud services have dominated large-scale LLM inference, cost and security concerns drive demand for on-premises deployment. Thus, GPU manufacturers have introduced personal AI computers (PAICs). However, existing PAICs with LPDDR-based unified main memory suffer from severe capacity limitations, restricting hostable LLM size on a single device. If most memory holds model weights, little remains for the KV cache, reducing supported context length.