<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>ONNX on AI VOID</title><link>https://ai-blog.noorshomelab.dev/tags/onnx/</link><description>Recent content in ONNX on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 07 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/tags/onnx/index.xml" rel="self" type="application/rss+xml"/><item><title>Deploying Gemma 4 QAT Models to Mobile and Laptop Environments</title><link>https://ai-blog.noorshomelab.dev/gemma-4-qat-guide-2026/deploying-to-edge-devices/</link><pubDate>Sun, 07 Jun 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/gemma-4-qat-guide-2026/deploying-to-edge-devices/</guid><description>&lt;h2 id="the-edge-advantage-deploying-gemma-4-qat-models"&gt;The Edge Advantage: Deploying Gemma 4 QAT Models&lt;/h2&gt;
&lt;p&gt;Welcome back, future AI architects! In previous chapters, we&amp;rsquo;ve explored the foundational power of Gemma 4 and the critical role of quantization in making large language models more efficient. Now, we&amp;rsquo;re going to put that knowledge into action by diving deep into the world of &lt;strong&gt;Quantization-Aware Training (QAT)&lt;/strong&gt; and its transformative impact on deploying Gemma 4 models to resource-constrained environments like mobile phones and laptops.&lt;/p&gt;</description></item></channel></rss>