SSD-LLaMA: SSD-Native Inference for Trillion-Parameter MoE at 1+ Token/s on a Consumer PC · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2609.18110/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTSSD-LLaMA: SSD-Native Inference for Trillion-Parameter MoE at 1+ Token/s on a Consumer PC — HN submissionhttps://news.ycombinator.com/item?id=49758274urn:hackerpapers:submission:2609.18110:49758274Fri, 18 Sep 2026 18:28:07 GMT<p>SSD-Llama: SSD-Native Inference for Trillion-Parameter Moe on a Consumer PC</p><p></p><p>3 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2609.18110/">Paper and source history</a>. A submission is not an endorsement.</p>cs.DC