<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ollama on Vivek Kumar</title><link>https://vkumar825.github.io/blog/ollama/</link><description>Recent content in Ollama on Vivek Kumar</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 21 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://vkumar825.github.io/blog/ollama/index.xml" rel="self" type="application/rss+xml"/><item><title>Setting Up Local LLMs on macOS</title><link>https://vkumar825.github.io/setting-up-local-llms-on-macos/</link><pubDate>Fri, 21 Aug 2026 00:00:00 +0000</pubDate><guid>https://vkumar825.github.io/setting-up-local-llms-on-macos/</guid><description>&lt;p&gt;In this post, I&amp;rsquo;ll go over how to set up local LLMs on macOS, though the same steps should also work on Windows if using Windows Subsystem for Linux (WSL). More on that in the next blog post, which will be about setting up Windows 11 for development!&lt;/p&gt;
&lt;p&gt;There are some reasons why it might be nice to have local LLMs on your computer, and one reason is that it is completely yours. Cloud-based LLMs like ChatGPT, Gemini, Grok, etc, tend to be very limiting because you are subject to the company&amp;rsquo;s policies on what you can and can&amp;rsquo;t do with it. It also offers complete privacy, the ability to access it offline, and no billing or usage limitations.&lt;/p&gt;</description></item></channel></rss>