{"id":18,"date":"2026-05-06T13:48:00","date_gmt":"2026-05-06T13:48:00","guid":{"rendered":"https:\/\/oliverng.com\/ai\/?p=18"},"modified":"2026-05-07T13:59:21","modified_gmt":"2026-05-07T13:59:21","slug":"gemma4-mtp","status":"publish","type":"post","link":"https:\/\/oliverng.com\/ai\/2026\/05\/06\/gemma4-mtp\/","title":{"rendered":"Gemma4 MTP"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Google released <a href=\"https:\/\/x.com\/googlegemma\/status\/2051694045869879749\" target=\"_blank\" rel=\"noreferrer noopener\">Gemma4 MTP<\/a> which incorporates a new feature, speculative decoding. Another lightweight model does token prediction speeding up the work for the larger model making the token speed up to 2-3x.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">I saw an cute ELI5:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"wp-block-paragraph\">Imagine two bears, a big slow bear and a little nimble bear looking for berries. The little bear runs off first and finds a bunch of berry trees and yells for the big bear. Big bear comes and decides which berry tree is most delicious and makes the final call to grab it.<\/p>\n<\/blockquote>\n\n\n\n<p class=\"wp-block-paragraph\">Unfortunately for me, my system still cant run it. <\/p>\n","protected":false},"excerpt":{"rendered":"<p>Google released Gemma4 MTP which incorporates a new feature, speculative decoding. Another lightweight model does token prediction speeding up the work for the larger model making the token speed up to 2-3x. I saw an cute ELI5: Imagine two bears, a big slow bear and a little nimble bear looking for berries. The little bear [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-18","post","type-post","status-publish","format-standard","hentry","category-models"],"_links":{"self":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts\/18","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/comments?post=18"}],"version-history":[{"count":4,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts\/18\/revisions"}],"predecessor-version":[{"id":24,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts\/18\/revisions\/24"}],"wp:attachment":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/media?parent=18"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/categories?post=18"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/tags?post=18"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}