{"id":26,"date":"2025-02-03T22:32:25","date_gmt":"2025-02-03T22:32:25","guid":{"rendered":"https:\/\/www.bgptrace.com\/blog\/?p=26"},"modified":"2025-02-04T22:44:29","modified_gmt":"2025-02-04T22:44:29","slug":"deepseek-1-5b-vs-8b","status":"publish","type":"post","link":"https:\/\/www.bgptrace.com\/blog\/?p=26","title":{"rendered":"Deepseek 1.5b vs 8b version"},"content":{"rendered":"\n<p>Well, we all expect that 1.5b and 8b may have a different of AI&#8217;s knowledge.  <\/p>\n\n\n\n<p>We made a test,  <br>1. 1.5b we are on Raspberry PI 4B 4G Ram.,  <br>2. 8b on virtual machine with AMD Radeon and 16G Ram on Ubuntu.<\/p>\n\n\n\n<p>We only ask a question.<\/p>\n\n\n\n<p>&#8220;what is the difference between you and chatGPT&#8221;<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>1. 1.5b versions<\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-large is-style-default\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"185\" src=\"https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-1024x185.png\" alt=\"\" class=\"wp-image-27\" srcset=\"https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-1024x185.png 1024w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-300x54.png 300w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-768x139.png 768w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image.png 1102w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 1362px) 62vw, 840px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"171\" src=\"https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-1-1024x171.png\" alt=\"\" class=\"wp-image-28\" srcset=\"https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-1-1024x171.png 1024w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-1-300x50.png 300w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-1-768x128.png 768w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-1-1536x256.png 1536w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-1-1200x200.png 1200w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-1.png 1786w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 1362px) 62vw, 840px\" \/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>2. 8b versions <\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"470\" src=\"https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-2-1024x470.png\" alt=\"\" class=\"wp-image-29\" srcset=\"https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-2-1024x470.png 1024w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-2-300x138.png 300w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-2-768x353.png 768w, https:\/\/www.bgptrace.com\/blog\/wp-content\/uploads\/2025\/02\/image-2.png 1130w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 1362px) 62vw, 840px\" \/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<p>The knowledge base of course 8b will be better. However, we will most concern of the resource usage.  Can Raspberry PI CPU base can process this efficient?<\/p>\n\n\n\n<p>#deepseek #AI #CPU #raspberrypi #GPU #nvidia #CUDB #AMD<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Well, we all expect that 1.5b and 8b may have a different of AI&#8217;s knowledge. We made a test, 1. 1.5b we are on Raspberry PI 4B 4G Ram., 2. 8b on virtual machine with AMD Radeon and 16G Ram on Ubuntu. We only ask a question. &#8220;what is the difference between you and chatGPT&#8221; &hellip; <a href=\"https:\/\/www.bgptrace.com\/blog\/?p=26\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Deepseek 1.5b vs 8b version&#8221;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":27,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[36,54,49,39,41,56,37,51,55,44,43,45,42,53,38,48,46],"class_list":["post-26","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","tag-ai","tag-ai-model","tag-amd","tag-chatgpt","tag-china","tag-cudb","tag-deepseek","tag-gpu","tag-model","tag-ram","tag-raspberry-pi","tag-raspberry-pi-4b","tag-raspberrypi","tag-ubuntu","tag-version","tag-vm","tag-vmware"],"_links":{"self":[{"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/26","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=26"}],"version-history":[{"count":3,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/26\/revisions"}],"predecessor-version":[{"id":38,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/26\/revisions\/38"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/media\/27"}],"wp:attachment":[{"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=26"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=26"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=26"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}