<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Evaluation Methodology on 67AI Lab</title>
    <link>https://67ailab.com/tags/evaluation-methodology/</link>
    <description>Recent content in Evaluation Methodology on 67AI Lab</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 12 Nov 2026 14:40:00 +0000</lastBuildDate>
    <atom:link href="https://67ailab.com/tags/evaluation-methodology/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>62 GPU-Hours on One Box: How We Ran a Small-Model Evaluation on a DGX Spark</title>
      <link>https://67ailab.com/posts/spark-eval-02-evaluation-process/</link>
      <pubDate>Thu, 12 Nov 2026 14:40:00 +0000</pubDate>
      <guid>https://67ailab.com/posts/spark-eval-02-evaluation-process/</guid>
      <description>&lt;p&gt;The other parts of this series ask what small models can do. This one is&#xA;about how we found out: what it takes to run five open models through eight&#xA;real tasks, two API references and a fine-tune, on one desk-side machine.&lt;/p&gt;&#xA;&lt;p&gt;That machine is an NVIDIA DGX Spark: a GB10 Grace Blackwell chip with&#xA;&lt;strong&gt;121 GB of unified memory&lt;/strong&gt;, meaning the CPU and GPU share one pool, on an&#xA;aarch64 (ARM) system. Unified memory is the Spark&amp;rsquo;s appeal, since a 35B model&#xA;fits easily. It also means every process on the box draws from the same pool:&#xA;the model, the test containers, your other services, even the agent driving&#xA;the study.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
