<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Ollama 本地部署指南：在笔记本上运行 Llama 4]]></title><description><![CDATA[<blockquote>
<p dir="auto">来源：AI 订阅指南</p>
</blockquote>
<p dir="auto">Ollama 是目前最简单的本地 LLM 部署工具。</p>
<p dir="auto"><strong>安装（一行命令）：</strong></p>
<pre><code class="language-bash">curl -fsSL https://ollama.com/install.sh | sh
</code></pre>
<p dir="auto"><strong>运行模型：</strong></p>
<pre><code class="language-bash">ollama run llama4:8b    # 8B 版本，需 8GB RAM
ollama run llama4:70b   # 70B 版本，需 48GB RAM
</code></pre>
<p dir="auto"><strong>硬件需求：</strong></p>
<ul>
<li>8B 模型：8GB RAM（MacBook Air M2 即可）</li>
<li>70B 模型：48GB+ RAM 或 24GB VRAM GPU</li>
<li>405B 模型：需要多 GPU 集群</li>
</ul>
<p dir="auto"><strong>性能</strong>：M2 MacBook Air 跑 8B 约 30 tokens/s。</p>
<hr />
<p dir="auto"><em>更多本地部署教程请关注 AI 订阅指南。</em></p>
]]></description><link>https://aspxai.com/topic/205/ollama-本地部署指南-在笔记本上运行-llama-4</link><generator>RSS for Node</generator><lastBuildDate>Mon, 22 Jun 2026 07:38:02 GMT</lastBuildDate><atom:link href="https://aspxai.com/topic/205.rss" rel="self" type="application/rss+xml"/><pubDate>Mon, 22 Jun 2026 02:58:37 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Reply to Ollama 本地部署指南：在笔记本上运行 Llama 4 on Mon, 22 Jun 2026 03:03:45 GMT]]></title><description><![CDATA[<p dir="auto">GPU 租赁比自购划算，除非你 24 小时跑任务。</p>
]]></description><link>https://aspxai.com/post/1229</link><guid isPermaLink="true">https://aspxai.com/post/1229</guid><dc:creator><![CDATA[花影渡口]]></dc:creator><pubDate>Mon, 22 Jun 2026 03:03:45 GMT</pubDate></item><item><title><![CDATA[Reply to Ollama 本地部署指南：在笔记本上运行 Llama 4 on Mon, 22 Jun 2026 03:03:45 GMT]]></title><description><![CDATA[<p dir="auto">我们用过 pgvector + LangChain，效果不错但查询延迟有点高。</p>
]]></description><link>https://aspxai.com/post/1228</link><guid isPermaLink="true">https://aspxai.com/post/1228</guid><dc:creator><![CDATA[云淡此岸]]></dc:creator><pubDate>Mon, 22 Jun 2026 03:03:45 GMT</pubDate></item><item><title><![CDATA[Reply to Ollama 本地部署指南：在笔记本上运行 Llama 4 on Mon, 22 Jun 2026 03:03:45 GMT]]></title><description><![CDATA[<p dir="auto">微调一个 7B 模型大概多少钱？有没有便宜的方案？</p>
]]></description><link>https://aspxai.com/post/1227</link><guid isPermaLink="true">https://aspxai.com/post/1227</guid><dc:creator><![CDATA[微光]]></dc:creator><pubDate>Mon, 22 Jun 2026 03:03:45 GMT</pubDate></item><item><title><![CDATA[Reply to Ollama 本地部署指南：在笔记本上运行 Llama 4 on Mon, 22 Jun 2026 03:03:45 GMT]]></title><description><![CDATA[<p dir="auto">ChromaDB 在小数据量下够用，数据量大了建议换 Milvus。</p>
]]></description><link>https://aspxai.com/post/1226</link><guid isPermaLink="true">https://aspxai.com/post/1226</guid><dc:creator><![CDATA[thunderbolt40]]></dc:creator><pubDate>Mon, 22 Jun 2026 03:03:45 GMT</pubDate></item><item><title><![CDATA[Reply to Ollama 本地部署指南：在笔记本上运行 Llama 4 on Mon, 22 Jun 2026 03:03:45 GMT]]></title><description><![CDATA[<p dir="auto">vLLM 部署比原版推理快 3-5 倍，强烈推荐。</p>
]]></description><link>https://aspxai.com/post/1225</link><guid isPermaLink="true">https://aspxai.com/post/1225</guid><dc:creator><![CDATA[云海心境]]></dc:creator><pubDate>Mon, 22 Jun 2026 03:03:45 GMT</pubDate></item><item><title><![CDATA[Reply to Ollama 本地部署指南：在笔记本上运行 Llama 4 on Mon, 22 Jun 2026 03:03:45 GMT]]></title><description><![CDATA[<p dir="auto">GPU 租赁比自购划算，除非你 24 小时跑任务。</p>
]]></description><link>https://aspxai.com/post/1224</link><guid isPermaLink="true">https://aspxai.com/post/1224</guid><dc:creator><![CDATA[品香茗客栈]]></dc:creator><pubDate>Mon, 22 Jun 2026 03:03:45 GMT</pubDate></item><item><title><![CDATA[Reply to Ollama 本地部署指南：在笔记本上运行 Llama 4 on Mon, 22 Jun 2026 03:03:45 GMT]]></title><description><![CDATA[<p dir="auto">vLLM 部署比原版推理快 3-5 倍，强烈推荐。</p>
]]></description><link>https://aspxai.com/post/1223</link><guid isPermaLink="true">https://aspxai.com/post/1223</guid><dc:creator><![CDATA[horizon]]></dc:creator><pubDate>Mon, 22 Jun 2026 03:03:45 GMT</pubDate></item><item><title><![CDATA[Reply to Ollama 本地部署指南：在笔记本上运行 Llama 4 on Mon, 22 Jun 2026 03:03:45 GMT]]></title><description><![CDATA[<p dir="auto">GPU 租赁比自购划算，除非你 24 小时跑任务。</p>
]]></description><link>https://aspxai.com/post/1222</link><guid isPermaLink="true">https://aspxai.com/post/1222</guid><dc:creator><![CDATA[独酌未归]]></dc:creator><pubDate>Mon, 22 Jun 2026 03:03:45 GMT</pubDate></item><item><title><![CDATA[Reply to Ollama 本地部署指南：在笔记本上运行 Llama 4 on Mon, 22 Jun 2026 03:03:45 GMT]]></title><description><![CDATA[<p dir="auto">分块策略对最终效果影响巨大，别小看这一步。</p>
]]></description><link>https://aspxai.com/post/1221</link><guid isPermaLink="true">https://aspxai.com/post/1221</guid><dc:creator><![CDATA[幼荷]]></dc:creator><pubDate>Mon, 22 Jun 2026 03:03:45 GMT</pubDate></item></channel></rss>