<?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>Llama on 技术博客 - 有条工具</title><link>/blog/tags/llama/</link><description>Recent content in Llama on 技术博客 - 有条工具</description><generator>Hugo -- 0.147.7</generator><language>zh-cn</language><copyright>2024-2025 有条工具技术博客</copyright><lastBuildDate>Sat, 03 Oct 2026 09:00:00 +0800</lastBuildDate><atom:link href="/blog/tags/llama/feed.xml" rel="self" type="application/rss+xml"/><item><title>2026 本地大模型选型指南：Qwen3 / Llama / DeepSeek 怎么选</title><link>/blog/articles/local-llm-model-comparison-2026/</link><pubDate>Sat, 03 Oct 2026 09:00:00 +0800</pubDate><guid>/blog/articles/local-llm-model-comparison-2026/</guid><description>从任务类型、硬件显存、量化生态与中文能力四个维度对比三大开源模型家族，给出 8G/16G/24G/48G 显存档位的选型清单，三分钟对号入座。</description></item></channel></rss>