A new open-source project called Janas enables running large language models (LLMs) that exceed a computer's available RAM by efficiently streaming model layers from a Solid State Drive (SSD). This technique allows for the execution of significantly larger models than previously possible on consumer hardware. The project's code is available on GitHub. AI
IMPACT Enables running larger LLMs on consumer hardware by optimizing memory management through SSD streaming.
RANK_REASON Open-source project release detailing a new technique for running large models. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Mastodon — mastodon.social →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →