<?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 Tim Harbakon</title><link>https://timharbakon.com/tags/local-llm/</link><description>Recent content in Local LLM on Tim Harbakon</description><generator>Hugo -- 0.165.0</generator><language>en-us</language><lastBuildDate>Sun, 16 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://timharbakon.com/tags/local-llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Qwen3.8-27B vs Gemma4-26B: RTX 4090 Benchmarks</title><link>https://timharbakon.com/qwen3-8-27b-vs-gemma4-26b-rtx-4090-benchmark/</link><pubDate>Sun, 16 Aug 2026 00:00:00 +0000</pubDate><guid>https://timharbakon.com/qwen3-8-27b-vs-gemma4-26b-rtx-4090-benchmark/</guid><description>Complete RTX 4090 guide to Qwen3.8-27B, Gemma4-26B, Ollama, and llama.cpp: installation, model profiles, context limits, vision, MTP, and benchmarks.</description></item></channel></rss>