{"blog_title":"Technically Impossible","provider_url":"https://hatena.blog","description":"Abstract If performance is not concern, whether it is GPT or Diffusion, they work on a machine with only 8GB RAM withuot GPU, be it on a PC or and Android smartphone. This is my finding from generative AI exploration in this spring*1. But there is a condition that inference only. In other words, it \u2026","width":"100%","title":"Llama2.c on PC with 8GB RAM, No GPU, No Container - pretokenization, training and inference","provider_name":"Hatena Blog","blog_url":"https://impsbl.hatenablog.jp/","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/e/espio999/20230827/20230827212158.png","type":"rich","categories":["AI","Clear Linux","English post","IT","Python","Windows","Linux"],"html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fimpsbl.hatenablog.jp%2Fentry%2Fllama2cWith8GB-RAM_en\" title=\"Llama2.c on PC with 8GB RAM, No GPU, No Container - pretokenization, training and inference - Technically Impossible\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","version":"1.0","height":"190","published":"2023-08-29 00:00:00","url":"https://impsbl.hatenablog.jp/entry/llama2cWith8GB-RAM_en","author_url":"https://blog.hatena.ne.jp/espio999/","author_name":"espio999"}