<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llamatik on</title><link>https://ferranpons.com/tags/llamatik/</link><description>Recent content in Llamatik on</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 28 Jan 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://ferranpons.com/tags/llamatik/index.xml" rel="self" type="application/rss+xml"/><item><title>How to Run LLMs Offline on Android Using Kotlin</title><link>https://ferranpons.com/blog/how-to-run-llms-offline-on-android-kotlin/</link><pubDate>Tue, 28 Jan 2025 00:00:00 +0000</pubDate><guid>https://ferranpons.com/blog/how-to-run-llms-offline-on-android-kotlin/</guid><description>&lt;p&gt;Cloud-based language models introduce network dependency, latency, usage-based costs, and privacy concerns. So the question is: can we run LLMs fully offline on Android, using Kotlin?&lt;/p&gt;
&lt;p&gt;The answer is yes — and it&amp;rsquo;s more practical than you might think.&lt;/p&gt;
&lt;h3 id="why-run-llms-offline-on-android"&gt;Why Run LLMs Offline on Android?&lt;/h3&gt;
&lt;p&gt;Offline LLMs enable:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Offline-first applications&lt;/li&gt;
&lt;li&gt;Privacy-preserving AI&lt;/li&gt;
&lt;li&gt;Predictable performance and cost&lt;/li&gt;
&lt;li&gt;Tight UI integration with no round-trip latency&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;Modern Android devices offer ARM CPUs with NEON support, substantial RAM on mid/high-end devices, and fast local storage. The challenge lies in tooling, not hardware.&lt;/p&gt;</description></item></channel></rss>