Open‑source WASTE runs 2.78‑trillion‑parameter LLM on consumer hardware
The WASTE engine streams the 2.78‑trillion‑parameter Kimi K3 model (982 GiB container) directly from NVMe, fitting the inference on a 64 GB MacBook Pro at 0.45‑0.62 tokens / s. It shows trillion‑scale LLMs can be run without server‑grade RAM, turning feasibility into an engineering challenge.