<?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>Llama-Cpp on martinuke0&#39;s Blog</title>
    <link>https://martinuke0.github.io/tags/llama-cpp/</link>
    <description>Recent content in Llama-Cpp on martinuke0&#39;s Blog</description>
    <image>
      <title>martinuke0&#39;s Blog</title>
      <url>https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</url>
      <link>https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</link>
    </image>
    <generator>Hugo -- 0.152.2</generator>
    <language>en</language>
    <lastBuildDate>Wed, 02 Sep 2026 20:00:49 +0000</lastBuildDate>
    <atom:link href="https://martinuke0.github.io/tags/llama-cpp/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Optimizing Small Language Models for Local Edge Inference: A Production-Ready Guide</title>
      <link>https://martinuke0.github.io/posts/2026-09-02-optimizing-small-language-models-for-local-edge-inference-a-production-ready-guide/</link>
      <pubDate>Wed, 02 Sep 2026 20:00:49 +0000</pubDate>
      <guid>https://martinuke0.github.io/posts/2026-09-02-optimizing-small-language-models-for-local-edge-inference-a-production-ready-guide/</guid>
      <description>A production-focused guide to running small language models on edge hardware: quantization, runtime choice, KV-cache tuning, and observability for real deployments.</description>
    </item>
  </channel>
</rss>
