[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"topic-en-googles-turboquant-cuts-llm-memory-costs":3},{"cluster":4,"timeline":17},{"id":5,"slug":6,"title":7,"pinned":8,"status":9,"summary":10,"category":11,"language":12,"created_at":13,"merged_into":14,"article_count":15,"first_seen_at":13,"last_updated_at":16},"ca8abee5-7632-4e34-80a8-db0f000a249f","googles-turboquant-cuts-llm-memory-costs","Google's TurboQuant Cuts LLM Memory Costs",false,"active","Google says TurboQuant uses QJL and PolarQuant to shrink vector-quantization memory and speed up LLM inference by up to 8x.","research","en","2026-07-05T09:01:57.718944+00:00",null,3,"2026-07-06T00:40:00.034514+00:00",[18],{"id":19,"slug":20,"title":21,"summary":22,"category":11,"image_url":23,"cover_image":23,"published_at":24,"is_canonical_seed":8},"6c80feee-7f7d-4518-bd06-3c04b8c46054","turboquant-cuts-memory-use-without-accuracy-loss-en","TurboQuant cuts memory use 6x without accuracy loss","Google Research’s TurboQuant claims 6x less memory and 8x faster inference with no accuracy loss, jolting AI inference economics.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775161136573-e0cb.png","2026-04-02T20:18:39.843+00:00"]