<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Uv on Mohammad Movahedi</title><link>https://m-movahedi.com/tags/uv/</link><description>Recent content in Uv on Mohammad Movahedi</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 29 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://m-movahedi.com/tags/uv/index.xml" rel="self" type="application/rss+xml"/><item><title>Local LLMs 202: The Local LLM Toolchain: uv, uvx, Ollama, and Model Files</title><link>https://m-movahedi.com/scratchpad/local-llms/local-llms-202-local-llm-toolchain-uv-uvx-ollama-model-files/</link><pubDate>Fri, 29 May 2026 00:00:00 +0000</pubDate><guid>https://m-movahedi.com/scratchpad/local-llms/local-llms-202-local-llm-toolchain-uv-uvx-ollama-model-files/</guid><description>&lt;p&gt;A local LLM setup can feel messy because several tools appear at once: Python environments, command-line utilities, model downloaders, model runtimes, chat interfaces, and APIs. The trick is to separate the toolchain into jobs.&lt;/p&gt;
&lt;p&gt;For a beginner, four ideas are enough to get oriented: &lt;code&gt;uv&lt;/code&gt;, &lt;code&gt;uvx&lt;/code&gt;, Ollama, and model files.&lt;/p&gt;
&lt;h2 id="mental-model-tools-install-things-runtimes-run-models"&gt;Mental model: tools install things, runtimes run models&lt;/h2&gt;
&lt;p&gt;&lt;code&gt;uv&lt;/code&gt; helps manage Python projects, Python versions, dependencies, and Python command-line tools. Ollama runs language models and exposes them through a local API. A model file contains the model weights and metadata that the runtime needs.&lt;/p&gt;</description></item></channel></rss>