{"published":"2025-09-02 00:00:00","author_name":"espio999","blog_title":"Technically Impossible","version":"1.0","description":"The emergence of llama.cpp*1 in 2023 made it possible to offload GPU processing to the CPU, making it a reality to run generative AI on a local environment. Even models that typically require a lot of VRAM can now be run on a system with as little as 8GB of RAM. The advent of LM Studio and SML (Smal\u2026","provider_url":"https://hatena.blog","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fimpsbl.hatenablog.jp%2Fentry%2FLMStudio_en\" title=\"LM Studio and SML on PC with 8GB RAM, No GPU - downloading models, starting server and agentic editing - 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>","author_url":"https://blog.hatena.ne.jp/espio999/","title":"LM Studio and SML on PC with 8GB RAM, No GPU - downloading models, starting server and agentic editing","width":"100%","blog_url":"https://impsbl.hatenablog.jp/","provider_name":"Hatena Blog","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/e/espio999/20250829/20250829225509.png","categories":["AI","English post","IT"],"type":"rich","url":"https://impsbl.hatenablog.jp/entry/LMStudio_en","height":"190"}