<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Local LLM on Fabian G. Williams</title><link>https://www.fabswill.com/categories/local-llm/</link><description>Recent content in Local LLM on Fabian G. Williams</description><image><title>Fabian G. Williams</title><url>https://www.fabswill.com/img/main/logo.jpg</url><link>https://www.fabswill.com/img/main/logo.jpg</link></image><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 09 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.fabswill.com/categories/local-llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Qwen 3.6 vs gpt-oss:120b on M3 Max: I Ran a Harder Test, the 8× Speed Gap Surprised Me</title><link>https://www.fabswill.com/blog/qwen-3-6-vs-gpt-oss-m3-max-8x-speed-gap-receipts/</link><pubDate>Sat, 09 May 2026 00:00:00 +0000</pubDate><guid>https://www.fabswill.com/blog/qwen-3-6-vs-gpt-oss-m3-max-8x-speed-gap-receipts/</guid><description>I published a Qwen 3.6 vs gpt-oss migration story, then ran an un-gameable eval against both on the same M3 Max. The receipts changed the speed narrative — gpt-oss:120b ran 8 to 11 times faster than qwen3.6:27b at parity reasoning quality. Here is the methodology and the data.</description></item></channel></rss>