<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai on Lusovps Blog</title><link>https://blog.lusovps.com/categories/ai/</link><description>Recent content in Ai on Lusovps Blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026</copyright><lastBuildDate>Thu, 12 Nov 2026 12:00:00 +0000</lastBuildDate><atom:link href="https://blog.lusovps.com/categories/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Qwen3-Coder 32B on a GPU server vs. GPT-4 on real code reviews</title><link>https://blog.lusovps.com/posts/qwen3-coder-32b-gpu-vs-gpt4-code-review/</link><pubDate>Thu, 12 Nov 2026 12:00:00 +0000</pubDate><guid>https://blog.lusovps.com/posts/qwen3-coder-32b-gpu-vs-gpt4-code-review/</guid><description>An open coding model on one GPU against a closed frontier API, on six real PRs graded blind by three engineers. GPT-4 caught more on security; Qwen3-Coder was quieter and hallucinated less.</description></item><item><title>Running Llama 3.1 8B on an 8 GB VPS, step by step</title><link>https://blog.lusovps.com/posts/running-llama-3-1-8b-on-an-8gb-vps/</link><pubDate>Wed, 11 Nov 2026 10:00:00 +0000</pubDate><guid>https://blog.lusovps.com/posts/running-llama-3-1-8b-on-an-8gb-vps/</guid><description>How to run Llama 3.1 8B on a single 8 GB VPS without a GPU, with the full set of commands and the throughput to expect.</description></item><item><title>Five open-source LLMs worth running in late 2026</title><link>https://blog.lusovps.com/posts/5-open-source-llms-worth-running-late-2026/</link><pubDate>Wed, 04 Nov 2026 10:00:00 +0000</pubDate><guid>https://blog.lusovps.com/posts/5-open-source-llms-worth-running-late-2026/</guid><description>Five models we deploy, the trade-offs of each for chat, code, agents and vision, and the minimum hardware each one needs.</description></item></channel></rss>