{"id":188,"date":"2026-08-22T07:24:39","date_gmt":"2026-08-22T07:24:39","guid":{"rendered":"https:\/\/emrahdiril.com\/notes\/?p=188"},"modified":"2026-08-28T07:27:24","modified_gmt":"2026-08-28T07:27:24","slug":"new-frontiers","status":"publish","type":"post","link":"https:\/\/emrahdiril.com\/notes\/new-frontiers\/","title":{"rendered":"New frontiers"},"content":{"rendered":"\n<p>Everyone is excited they can run large models on their home computers, and here I\u2019m wondering, can we run frontier models more cheaply in the cloud without requiring specialty GPU hardware that is very hard to secure even if you have the money?<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-rich is-provider-x wp-block-embed-x\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"twitter-tweet\" data-width=\"500\" data-dnt=\"true\"><p lang=\"en\" dir=\"ltr\">Your gaming PC can now serve frontier models at interactive speed using official checkpoints without extreme quantization!<br><br>Qwen3.6 35B \u2192 8GB RTX 4060 laptop @ 39 tok\/s<br><br>DeepSeek-V4-Flash 284B \u2192 RTX 5090 desktop @ 22-25 tok\/s<br><br>GLM-5.2 753B \u2192 RTX PRO 6000 workstation @ 15 tok\/s\u2026 <a href=\"https:\/\/t.co\/OjZMO3wJwy\">pic.twitter.com\/OjZMO3wJwy<\/a><\/p>&mdash; Shuo Yang (@Andy_ShuoYang) <a href=\"https:\/\/x.com\/Andy_ShuoYang\/status\/2090856976880472439?ref_src=twsrc%5Etfw\">August 21, 2026<\/a><\/blockquote><script async src=\"https:\/\/platform.x.com\/widgets.js\" charset=\"utf-8\"><\/script>\n<\/div><\/figure>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/abs\/2608.16157\">https:\/\/arxiv.org\/abs\/2608.16157<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/github.com\/FlashML-org\/FreeToken\">https:\/\/github.com\/FlashML-org\/FreeToken<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Everyone is excited they can run large models on their home computers, and here I\u2019m wondering, can we run frontier models more cheaply in the cloud without requiring specialty GPU hardware that is very hard to secure even if you have the money? https:\/\/arxiv.org\/abs\/2608.16157 https:\/\/github.com\/FlashML-org\/FreeToken<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14],"tags":[],"class_list":["post-188","post","type-post","status-publish","format-standard","hentry","category-ai"],"_links":{"self":[{"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/posts\/188","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/comments?post=188"}],"version-history":[{"count":1,"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/posts\/188\/revisions"}],"predecessor-version":[{"id":189,"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/posts\/188\/revisions\/189"}],"wp:attachment":[{"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/media?parent=188"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/categories?post=188"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/emrahdiril.com\/notes\/wp-json\/wp\/v2\/tags?post=188"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}