SemanticScuttle - klotz.me

klotz: 120b* + llm* + mixture of experts*

0 bookmark(s) - Sort by: Date ↓ / Title / - Bookmarks from other users for this tag

1. My mind was blown: running a 120B parameter AI model on a budget GPU at home

   A 120 billion parameter OpenAI model can now run on consumer hardware thanks to the Mixture of Experts (MoE) technique, which significantly reduces memory requirements and allows processing on CPUs while offloading key parts to modest GPUs.

   2025-08-21 Tags: llm, mixture of experts, 120b, gpu, cpu, openai, gpt-oss-120b by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0