<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Which model should I pick?]]></title><description><![CDATA[<p dir="auto">The honest answer: <strong>start with what setup recommends</strong>, then move up only if your machine looks bored.</p>
<p dir="auto">Rough guide by memory:</p>
<table class="table table-bordered table-striped">
<thead>
<tr>
<th>RAM</th>
<th>Sensible starting point</th>
</tr>
</thead>
<tbody>
<tr>
<td>8 GB</td>
<td>1–3B model, Q4</td>
</tr>
<tr>
<td>16 GB</td>
<td>3–8B model, Q4</td>
</tr>
<tr>
<td>32 GB+</td>
<td>8B and above, Q4–Q6</td>
</tr>
</tbody>
</table>
<p dir="auto"><strong>What the Q number means:</strong> compression. Q4 is roughly a quarter the size of the original with quality most people can't distinguish in normal use. Lower numbers are smaller and noticeably worse; higher are bigger and only marginally better. <strong>Q4 is the sweet spot</strong> and it's why it's the default.</p>
<p dir="auto">Bigger is not automatically better — a 3B model that fits comfortably will feel far better to use than an 8B one that makes your machine swap.</p>
<p dir="auto">What did setup suggest for you, and did you stick with it?</p>
]]></description><link>https://community.lizard-llm.qendryx.com/topic/18/which-model-should-i-pick</link><generator>RSS for Node</generator><lastBuildDate>Mon, 24 Aug 2026 01:37:29 GMT</lastBuildDate><atom:link href="https://community.lizard-llm.qendryx.com/topic/18.rss" rel="self" type="application/rss+xml"/><pubDate>Wed, 15 Jul 2026 10:42:00 GMT</pubDate><ttl>60</ttl></channel></rss>