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

Janas-LLM, a new method for running large language models (LLMs) larger than RAM by streaming experts from SSD, significantly outperforms llama.cpp. On a laptop with 32 GB of memory, Janas-LLM achieved 37 tok/s with Qwen3-Next-80B (a 48 GB model), compared to llama.cpp's 2.8 tok/s. For reading prompts, Janas-LLM reached 62 tok/s against llama.cpp's 16 tok/s. This performance advantage was consistent across various models tested on the same hardware.