{"id":13489,"date":"2024-03-29T20:38:07","date_gmt":"2024-03-29T19:38:07","guid":{"rendered":"https:\/\/roglacup.com\/klaus62\/?p=13489"},"modified":"2024-03-31T20:47:29","modified_gmt":"2024-03-31T19:47:29","slug":"5-easy-ways-to-run-an-llm-locally-infoworld","status":"publish","type":"post","link":"https:\/\/roglacup.com\/klaus62\/2024\/03\/29\/5-easy-ways-to-run-an-llm-locally-infoworld\/","title":{"rendered":"5 easy ways to run an LLM locally | InfoWorld"},"content":{"rendered":"\n<p>Chatbots like&nbsp;<a href=\"https:\/\/chat.openai.com\/\" rel=\"noreferrer noopener\" target=\"_blank\">ChatGPT<\/a>,&nbsp;<a href=\"https:\/\/claude.ai\/\" rel=\"noreferrer noopener\" target=\"_blank\">Claude.ai<\/a>, and&nbsp;<a href=\"https:\/\/www.phind.com\/\" rel=\"noreferrer noopener\" target=\"_blank\">phind<\/a>&nbsp;can be quite helpful, but you might not always want your questions or sensitive data handled by an external application. That&#8217;s especially true on platforms where your interactions may be reviewed by humans and otherwise used to help train future models.<\/p>\n\n\n\n<p>One solution is to download a&nbsp;<a href=\"https:\/\/www.infoworld.com\/article\/3700869\/14-llms-that-arent-chatgpt.html\" rel=\"noreferrer noopener\" target=\"_blank\">large language model (LLM)<\/a>&nbsp;and run it on your own machine. That way, an outside company never has access to your data. This is also a quick option to try some new specialty models such as Meta&#8217;s recently announced&nbsp;<a href=\"https:\/\/www.infoworld.com\/article\/3705588\/meta-unleashes-ai-llm-for-coding.html\" rel=\"noreferrer noopener\" target=\"_blank\">Code Llama family of models<\/a>, which are tuned for coding, and&nbsp;<a href=\"https:\/\/ai.meta.com\/blog\/seamless-m4t\/\" rel=\"noreferrer noopener\" target=\"_blank\">SeamlessM4T<\/a>, aimed at text-to-speech and language translations.<\/p>\n\n\n\n<p>Running your own LLM might sound complicated, but with the right tools, it\u2019s surprisingly easy. And the hardware requirements for many models aren\u2019t crazy. I&#8217;ve tested the options presented in this article on two systems: a Dell PC with an Intel i9 processor, 64GB of RAM, and a Nvidia GeForce 12GB GPU (which likely wasn&#8217;t engaged running much of this software), and on a Mac with an M1 chip but just 16GB of RAM.&nbsp;<\/p>\n\n\n\n<p><a href=\"https:\/\/www.infoworld.com\/article\/3705035\/5-easy-ways-to-run-an-llm-locally.html\">https:\/\/www.infoworld.com\/article\/3705035\/5-easy-ways-to-run-an-llm-locally.html<\/a><\/p>\n\n\n\n<h1 class=\"wp-block-heading\">How To Get Started With Code Llama<\/h1>\n\n\n\n<p>The purpose of this article is to help readers easily get up and running with Code Llama. We&#8217;ll cover the main ways to access Code Llama&#8217;s capabilities both locally or via hosted services.<\/p>\n\n\n\n<p>Posted from: <a href=\"https:\/\/www.maginative.com\/article\/how-to-get-started-with-code-llama\/\">https:\/\/www.maginative.com\/article\/how-to-get-started-with-code-llama\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Chatbots like&nbsp;ChatGPT,&nbsp;Claude.ai, and&nbsp;phind&nbsp;can be quite helpful, but you might not always want your questions or sensitive data handled by an external application. That&#8217;s especially true on platforms where your interactions may be reviewed by humans and otherwise used to help train future models. One solution is to download a&nbsp;large language model (LLM)&nbsp;and run it on&hellip;&nbsp;<a href=\"https:\/\/roglacup.com\/klaus62\/2024\/03\/29\/5-easy-ways-to-run-an-llm-locally-infoworld\/\" class=\"\" rel=\"bookmark\">Read More &raquo;<span class=\"screen-reader-text\">5 easy ways to run an LLM locally | InfoWorld<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":13511,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"categories":[812,1686],"tags":[],"class_list":["post-13489","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","category-lmm"],"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/posts\/13489","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/comments?post=13489"}],"version-history":[{"count":3,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/posts\/13489\/revisions"}],"predecessor-version":[{"id":13513,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/posts\/13489\/revisions\/13513"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/media\/13511"}],"wp:attachment":[{"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/media?parent=13489"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/categories?post=13489"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/tags?post=13489"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}