<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>LLM Local on Wiliam Rosa | Lakehouse, Dados &amp; IA</title>
    <link>https://wiliamrosa.github.io/tags/llm-local/</link>
    <description>Recent content in LLM Local on Wiliam Rosa | Lakehouse, Dados &amp; IA</description>
    <image>
      <title>Wiliam Rosa | Lakehouse, Dados &amp; IA</title>
      <url>https://wiliamrosa.github.io/images/wiliam-rosa-blog-og.png</url>
      <link>https://wiliamrosa.github.io/images/wiliam-rosa-blog-og.png</link>
    </image>
    <generator>Hugo</generator>
    <language>pt-br</language>
    <lastBuildDate>Fri, 04 Sep 2026 09:00:00 -0300</lastBuildDate>
    <atom:link href="https://wiliamrosa.github.io/tags/llm-local/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Rodei o Omnigent com um LLM local no Mac, e a configuração levou menos de 30 minutos</title>
      <link>https://wiliamrosa.github.io/posts/omnigent-llm-local-llama-cpp/</link>
      <pubDate>Fri, 04 Sep 2026 09:00:00 -0300</pubDate>
      <guid>https://wiliamrosa.github.io/posts/omnigent-llm-local-llama-cpp/</guid>
      <description>Configurar o Omnigent para rodar com um modelo quantizado local via llama.cpp é mais simples do que parece, e ainda revela que o Ollama, apesar de mais popular, é mais lento e mais trabalhoso de configurar pro mesmo modelo.</description>
    </item>
  </channel>
</rss>
