<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ollama on myvirtualcloud.net</title><link>https://myvirtualcloud.net/tags/ollama/</link><description>Recent content in Ollama on myvirtualcloud.net</description><generator>Hugo</generator><language>en-us</language><copyright>Andre Leibovici</copyright><lastBuildDate>Thu, 11 Jun 2026 09:00:00 +1200</lastBuildDate><atom:link href="https://myvirtualcloud.net/tags/ollama/index.xml" rel="self" type="application/rss+xml"/><item><title>How our document classifier votes before it ever asks a language model</title><link>https://myvirtualcloud.net/how-our-document-classifier-votes-before-it-ever-asks-a-language-model/</link><pubDate>Thu, 11 Jun 2026 09:00:00 +1200</pubDate><guid>https://myvirtualcloud.net/how-our-document-classifier-votes-before-it-ever-asks-a-language-model/</guid><description>&lt;p&gt;A district council we work with has about 4 TB of files in SharePoint and more on internal SMB shares, and they need to know what is in them: which documents are contracts, which hold personal information, and which should have been disposed of years ago under the Public Records Act 2005. Every one of those files has to be read, classified into one of roughly 30 document types, and scored for sensitivity.&lt;/p&gt;</description></item><item><title>Announcing the Ollama GPU Calculator</title><link>https://myvirtualcloud.net/announcing-the-ollama-gpu-calculator/</link><pubDate>Mon, 28 Oct 2024 05:37:02 +0000</pubDate><guid>https://myvirtualcloud.net/announcing-the-ollama-gpu-calculator/</guid><description>&lt;p&gt;If you have spent any time running local models with Ollama, you already know the awkward part: picking a model is easy; knowing whether your GPU can actually host it is not. Parameter count, quantization, context length, and VRAM interact in ways that are hard to eyeball — especially once you start mixing cards or looking at Apple Silicon unified memory.&lt;/p&gt;</description></item></channel></rss>