Post #233826 479 Oct 13, 2026, 01:57 UTC Janas: Run LLMs larger than RAM by streaming experts from SSDArticle, Comments GitHub GitHub - prabanta-dev/janas: 37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading… 37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than y... 🥰 3 🤔 2 🌭 1