<?xml version="1.0" encoding="utf-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
	<channel>
		<title>ProZ.com Translation Forums</title>
		<link>http://ben.proz.com/forums/</link>
		<atom:link href="http://ben.proz.com/forums/" rel="self" type="application/rss+xml"/>		<description>Topic: Using LLMs Directly in Trados Studio: A Plugin Worth Exploring</description>
		<language>en-us</language>
		<pubDate>Fri, 02 Oct 2026 06:44:53 +0000</pubDate>
		<lastBuildDate>Fri, 02 Oct 2026 06:44:53 +0000</lastBuildDate>
		<docs>http://www.proz.com/faq</docs>
		<managingEditor>support@proz.com (ProZ.com Support)</managingEditor>
		<webMaster>support@proz.com (ProZ.com Support)</webMaster>
		<item>
			<title>Using LLMs Directly in Trados Studio: A Plugin Worth Exploring | Ollama</title>
			<author>Li-Hsiang Hsu</author>
			<category>Translator resources</category>
			<link>http://ben.proz.com/post/3120515#3120515</link>
			<pubDate>Fri, 02 Oct 2026 06:03:00 +0000</pubDate>
			<description>&lt;b&gt;Forum:&lt;/b&gt; Translator resources&lt;br/&gt;&lt;b&gt;Topic:&lt;/b&gt; Using LLMs Directly in Trados Studio: A Plugin Worth Exploring&lt;br/&gt;&lt;b&gt;Poster:&lt;/b&gt; Li-Hsiang Hsu&lt;br/&gt;&lt;b&gt;Post title:&lt;/b&gt; Ollama&lt;br/&gt;&lt;br/&gt;Wow, Supervertaler has a serious competitor! 😂&lt;br /&gt;&lt;br /&gt;Ollama seems to be running very fast on your PC. Is it Ollama Cloud? I use Ollama locally on my gamer PC, which has a decent GPU, but it struggles with newer models like Gemma 4 and Qwen.</description>
		</item>
		<item>
			<title>Using LLMs Directly in Trados Studio: A Plugin Worth Exploring</title>
			<author>Mohamed Zeid</author>
			<category>Translator resources</category>
			<link>http://ben.proz.com/post/3120506#3120506</link>
			<pubDate>Thu, 01 Oct 2026 19:50:00 +0000</pubDate>
			<description>&lt;b&gt;Forum:&lt;/b&gt; Translator resources&lt;br/&gt;&lt;b&gt;Topic:&lt;/b&gt; Using LLMs Directly in Trados Studio: A Plugin Worth Exploring&lt;br/&gt;&lt;b&gt;Poster:&lt;/b&gt; Mohamed Zeid&lt;br/&gt;&lt;br/&gt;I wanted to share a tool that I think may be of interest to translators who have been experimenting with LLMs in their workflow.&lt;br /&gt;&lt;br /&gt;It&#039;s called TransLLM, and it&#039;s a plugin for Trados Studio that lets you connect Trados directly to LLMs. What I found particularly interesting is that it can work with local models through LM Studio or Ollama, so it is possible to translate without sending the actual translation content to a cloud service.&lt;br /&gt;&lt;br /&gt;It can also connect to cloud-based models if preferred, and it includes some features that are particularly relevant to translation work. For example, you can use glossaries to help guide terminology, create custom prompts for different types of content, and work with tagged segments.&lt;br /&gt;&lt;br /&gt;The glossary functionality is especially useful when you want the model to follow preferred terminology instead of translating everything freely. Tag preservation is also supported, which is important when working with formatted or tagged content in Trados. In my experience, tag handling is not always perfect, so it is still something I would check carefully, but it is definitely useful to have the functionality built into the workflow.&lt;br /&gt;&lt;br /&gt;For me, the interesting part is less about &quot;AI translation&quot; itself and more about being able to experiment with different translation models directly inside the CAT tool instead of copying segments back and forth between Trados and an external interface.&lt;br /&gt;&lt;br /&gt;Of course, the translation quality depends heavily on the model being used, and running models locally also requires appropriate hardware and some setup, so it will not necessarily be the right solution for everyone.&lt;br /&gt;&lt;br /&gt;I thought I would share it here since there have been quite a few discussions about LLMs, confidentiality, terminology control, and their possible use in professional translation workflows.&lt;br /&gt;&lt;br /&gt; [url removed] &lt;br /&gt;&lt;br /&gt;I&#039;d be interested to hear whether anyone else here has experimented with local LLMs inside Trados or another CAT tool, especially when it comes to terminology and tag handling.</description>
		</item>
	</channel>
</rss>