US deep-tech AI startup Tiiny AI has released a groundbreaking demonstration showing a 14-year-old PC running a 120-billion-parameter AI model smoothly without any internet connection. <\/p>\n
Captured in a single uninterrupted take, the demo features OpenAI\u2019s GPT-OSS 120B running on Pocket Lab, the company\u2019s proprietary personal supercomputer.<\/p>\n
Tiiny AI aims to make cloud-grade large language model intelligence accessible to everyone, regardless of internet connection, cloud access, or GPU upgrades. The company\u2019s Pocket Lab PC recently gained recognition as \u201cThe Smallest MiniPC (100B LLM Locally)\u201d, post its launch on December 10.<\/p>\n
Equipped with a 65W power capacity, it supports installation of popular open-source models like Llama, Qwen, DeepSeek, MIstral, Phi, and GPT-OSS.<\/p>\n
More on the experiment<\/p>\n
See 120B LLM Running Locally on an Old PC
in One Continuous Take<\/p>\n
No cloud. No GPU upgrade. No expensive computer.<\/p>\n
\ud83d\ude0e We just ran OpenAI GPT-OSS 120B on a computer from 14 years ago \u2014 powered by Tiiny AI Pocket Lab.<\/p>\n
See what personal AI actually looks like. pic.twitter.com\/6uaAOMH0oP<\/a><\/p>\n \u2014 Tiiny AI (@TiinyAILab) December 25, 2025<\/a><\/p>\n For the demo, the Tiiny AI team used a 2011 PC with an Intel Core i3-530 processor, 2GB of DDR3 RAM, and a CRT monitor. After connecting Pocket Lab to the old PC, the machine successfully operated ChatGPT<\/a>, with an average token processing speed of 20 tokens per second.<\/p>\n The team ran reasoning and analytical tasks on the PC in the demo. The chat started with a question prompt asking, \u201cWho are you?\u201d Next, the team queried \u201cWhy does 1+1=2\u201d, and the LLM launched<\/a> into a detailed explanation of the question without any interruptions. It used 1582 tokens to answer the question with a speed of 18.6 tokens per second.<\/p>\n \u201cThis demonstration proves something the AI industry long assumed was impossible,\u201d said Samar Bhoj, GTM Director of Tiiny AI.<\/p>\n \u201cWe are showing that large-model intelligence no longer needs massive GPU clusters or cloud infrastructure. With Tiiny AI Pocket Lab, advanced AI can run privately, offline, and on everyday hardware, even a 14-year-old PC. The future of AI belongs to people, not data centers,\u201d he added further.<\/p>\n By moving inference fully to the device, the demonstration proves that even older hardware can now deliver performance previously believed to require advanced AI systems.<\/p>\n What makes the AI supercomputer tick?<\/p>\n