Janas: Run LLMs larger than RAM by streaming experts from SSD

Janas streams LLM experts from SSD so models larger than RAM can run locally.

Janas is a GitHub project for running large language models that do not fit in system memory by streaming experts from an SSD. The Hacker News thread had 43 points and 20 comments. No model names, benchmarks, or release details were included in the listing.