{"id":1584,"date":"2025-02-01T07:03:23","date_gmt":"2025-02-01T07:03:23","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/02\/01\/2-bit-vptq-6-5x-smaller-llms-while-preserving-95-accuracy-41fb3c2b6f70\/"},"modified":"2025-02-01T07:03:23","modified_gmt":"2025-02-01T07:03:23","slug":"2-bit-vptq-6-5x-smaller-llms-while-preserving-95-accuracy-41fb3c2b6f70","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/02\/01\/2-bit-vptq-6-5x-smaller-llms-while-preserving-95-accuracy-41fb3c2b6f70\/","title":{"rendered":"2-Bit VPTQ: 6.5x Smaller LLMs While Preserving 95% Accuracy"},"content":{"rendered":"<p>    2-Bit VPTQ: 6.5x Smaller LLMs While Preserving 95% Accuracy<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>\n<div class=\"medium-feed-item\">\n<p class=\"medium-feed-image\"><a href=\"https:\/\/medium.com\/towards-data-science\/2-bit-vptq-6-5x-smaller-llms-while-preserving-95-accuracy-41fb3c2b6f70\"><img data-recalc-dims=\"1\" decoding=\"async\" src=\"https:\/\/i0.wp.com\/cdn-images-1.medium.com\/max\/1143\/0%2AMkC-gnCl8vmVVs9x.png?w=1143&#038;ssl=1\" ><\/a><\/p>\n<p class=\"medium-feed-snippet\">Very accurate 2-bit quantization for running 70B LLMs on a 24 GB GPU<\/p>\n<p class=\"medium-feed-link\"><a href=\"https:\/\/medium.com\/towards-data-science\/2-bit-vptq-6-5x-smaller-llms-while-preserving-95-accuracy-41fb3c2b6f70\">Continue reading on Towards Data Science \u00bb<\/a><\/p>\n<\/div>\n<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Benjamin Marie<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/medium.com\/towards-data-science\/2-bit-vptq-6-5x-smaller-llms-while-preserving-95-accuracy-41fb3c2b6f70\">Go to original source<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>2-Bit VPTQ: 6.5x Smaller LLMs While Preserving 95% Accuracy Very accurate 2-bit quantization for running 70B LLMs on a 24 GB GPU Continue reading on Towards Data Science \u00bb Benjamin Marie Go to original source<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,69,83,70,160,1574],"tags":[1575,318,1576],"class_list":["post-1584","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-artificial-intelligence","category-data-science","category-machine-learning","category-programming","category-quantization","tag-bit","tag-llms","tag-vptq"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/1584"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=1584"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/1584\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=1584"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=1584"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=1584"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}