Nextorage, a Japanese storage company and Phison subsidiary, announced the aiDAPTIV Station on July 28, 2026, an external device that plugs into a laptop's USB-C port and promises to run 120-billion-parameter models on a standard notebook with just 32GB of RAM. The device uses Phison aiDAPTIV+ memory offload technology, where a middleware layer dynamically shifts inactive data between system RAM, GPU memory, and a high-endurance NVMe SSD cache using SLC NAND rated at 100 DWPD. Nextorage acknowledges that USB-C bandwidth is narrower than a PCIe slot, so token generation will be slower than a dedicated GPU rig. The hardware is bundled with an "AI Standard Package" including an LLM execution engine, domain-specific sample data, and knowledge tools, supporting both Windows and Ubuntu Linux. A launch in Japan is targeted for end of 2026; no UK or US release date, retail price, or distribution partner has been named. Nextorage says the price will be lower than professional GPUs with 48GB or more of VRAM, while the RTX 5090 currently sells for $3,600–5,000 on the street. Running inference locally avoids sending sensitive queries to cloud servers, which matters for sectors under UK ICO or US data-protection scrutiny.