<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet href="https://kamilborys.com/feed_style.xsl" type="text/xsl"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
    <tabi:metadata xmlns:tabi="https://github.com/welpo/tabi">
        <tabi:base_url>https:&#x2F;&#x2F;kamilborys.com</tabi:base_url>
        <tabi:separator>
            •
        </tabi:separator>
        <tabi:about_feeds>This is a web feed, also known as an Atom feed. Subscribe by copying the URL from the address bar into your newsreader. Visit About Feeds to learn more and get started. It&#x27;s free.</tabi:about_feeds>
        <tabi:visit_the_site>Visit website</tabi:visit_the_site>
        <tabi:recent_posts>Recent posts</tabi:recent_posts>
        <tabi:last_updated_on>Updated on $DATE</tabi:last_updated_on>
        <tabi:default_theme>dark</tabi:default_theme>
        <tabi:post_listing_date>date</tabi:post_listing_date>
        <tabi:current_section>tinystories</tabi:current_section>
    </tabi:metadata><link rel="extra-stylesheet" href="https://kamilborys.com/skins/amber.css?h=f8925a89cfb5bc099f43" /><title>KamilCase - tinystories</title>
    <link href="https://kamilborys.com/tags/tinystories/atom.xml" rel="self" type="application/atom+xml"/>
    <link href="https://kamilborys.com/tags/tinystories/" rel="alternate" type="text/html"/>
    <generator uri="https://www.getzola.org/">Zola</generator>
    <updated>2026-01-24T00:00:00+00:00</updated>
    <id>https://kamilborys.com/tags/tinystories/atom.xml</id><entry xml:lang="en">
        <title>Tell me a Tiny Story: LLM Inference on a PowerMac G3</title>
        <published>2026-01-24T00:00:00+00:00</published>
        <updated>2026-01-24T00:00:00+00:00</updated>
        <author>
            <name>Kamil Borys</name>
        </author>
        <link rel="alternate" href="https://kamilborys.com/blog/tell-me-a-tiny-story/" type="text/html"/>
        <id>https://kamilborys.com/blog/tell-me-a-tiny-story/</id>
        <summary type="html">AI-generated content is everywhere now.
Your morning Instagram doom-scrolling routine,
those 47 unread emails in your inbox that arrived overnight,
the friendly assistant that tells you that you are absolutely right -
I'm sure at least some of that was powered by large language models.
These are usually run on powerful hardware,
in large fancy data centers consuming ridiculous amounts of power.
But what if I told you it's possible to run AI
from the comfort of your own home, right on your PowerMac G3 workstation?
~/src/llama2.c % uname -srm
NetBSD 10.1 macppc

~/src/llama2.c % ./run sw-stories15M.bin \
  -z sw-tokenizer.bin \
  -i &#39;Mary had a little lamb.&#39;
Mary had a little lamb.
She was very gentle and kind.
One day she was walking in the forest
when she saw something very strange.
There was a dragon
and it was making a loud roar.
(...)
achieved tok/s: 2.702613
…</summary>
        </entry>
</feed>
