<?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[AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo]]></title><description><![CDATA[<p dir="auto">我有一片MAXSUN Intel Arc Pro B60 Dual 48G Turbo，这个应该怎么使用？能部署啥本地模型？</p>
]]></description><link>https://lcz.me/topic/5/ai本地部署maxsun-intel-arc-pro-b60-dual-48g-turbo</link><generator>RSS for Node</generator><lastBuildDate>Wed, 20 May 2026 08:46:56 GMT</lastBuildDate><atom:link href="https://lcz.me/topic/5.rss" rel="self" type="application/rss+xml"/><pubDate>Sun, 03 May 2026 03:38:58 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Reply to AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo on Tue, 05 May 2026 18:05:09 GMT]]></title><description><![CDATA[<p dir="auto">趁它還是新的, 趕緊賣掉換卡吧</p>
]]></description><link>https://lcz.me/post/247</link><guid isPermaLink="true">https://lcz.me/post/247</guid><dc:creator><![CDATA[Peace Love]]></dc:creator><pubDate>Tue, 05 May 2026 18:05:09 GMT</pubDate></item><item><title><![CDATA[Reply to AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo on Mon, 04 May 2026 17:51:05 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/19-%E5%BE%90%E7%A6%8F%E6%94%BF" aria-label="Profile: 19-徐福政">@<bdi>19-徐福政</bdi></a> 便宜货效果都不行，不要折腾。老老实实买24G 3090， 7900xtx，35b a3b跑起来吃力，显存紧张，但是27b时本地之王，吊打35b。</p>
]]></description><link>https://lcz.me/post/125</link><guid isPermaLink="true">https://lcz.me/post/125</guid><dc:creator><![CDATA[terry]]></dc:creator><pubDate>Mon, 04 May 2026 17:51:05 GMT</pubDate></item><item><title><![CDATA[Reply to AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo on Mon, 04 May 2026 15:16:32 GMT]]></title><description><![CDATA[<p dir="auto">只跑 Qwen3.6 27b Qwen3.6-35B-A3B   a660 16g X2 能跑嗎  鹹魚 2000多能買到<br />
或是其他 2000-3000 能買到什麼能跑的嗎?</p>
]]></description><link>https://lcz.me/post/109</link><guid isPermaLink="true">https://lcz.me/post/109</guid><dc:creator><![CDATA[19-徐福政]]></dc:creator><pubDate>Mon, 04 May 2026 15:16:32 GMT</pubDate></item><item><title><![CDATA[Reply to AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo on Mon, 04 May 2026 03:39:44 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/%E5%88%98%E6%B5%B7%E5%BD%AC" aria-label="Profile: 刘海彬">@<bdi>刘海彬</bdi></a> 后期可能模型就不是27b了，如果是35b，那24G显存就紧张了。</p>
]]></description><link>https://lcz.me/post/70</link><guid isPermaLink="true">https://lcz.me/post/70</guid><dc:creator><![CDATA[terry]]></dc:creator><pubDate>Mon, 04 May 2026 03:39:44 GMT</pubDate></item><item><title><![CDATA[Reply to AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo on Mon, 04 May 2026 03:20:06 GMT]]></title><description><![CDATA[<p dir="auto">按照这个趋势，后续的模型估计越来越给力，玩本地AI的估计有福了</p>
]]></description><link>https://lcz.me/post/68</link><guid isPermaLink="true">https://lcz.me/post/68</guid><dc:creator><![CDATA[刘海彬]]></dc:creator><pubDate>Mon, 04 May 2026 03:20:06 GMT</pubDate></item><item><title><![CDATA[Reply to AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo on Mon, 04 May 2026 01:58:11 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/%E5%A2%99%E5%86%85%E4%BA%BA" aria-label="Profile: 墙内人">@<bdi>墙内人</bdi></a> 是的，qwen3.5 3.6 27b是现象级模型，本地最能打。</p>
]]></description><link>https://lcz.me/post/65</link><guid isPermaLink="true">https://lcz.me/post/65</guid><dc:creator><![CDATA[terry]]></dc:creator><pubDate>Mon, 04 May 2026 01:58:11 GMT</pubDate></item><item><title><![CDATA[Reply to AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo on Sun, 03 May 2026 17:19:33 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/seewoscott" aria-label="Profile: seewoscott">@<bdi>seewoscott</bdi></a> 黄金尺寸Gemma4 31B，但是不如Qwen3.5 36. 27b</p>
]]></description><link>https://lcz.me/post/48</link><guid isPermaLink="true">https://lcz.me/post/48</guid><dc:creator><![CDATA[墙内人]]></dc:creator><pubDate>Sun, 03 May 2026 17:19:33 GMT</pubDate></item><item><title><![CDATA[Reply to AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo on Sun, 03 May 2026 08:02:40 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/terry" aria-label="Profile: terry">@<bdi>terry</bdi></a> Gemma4这种多模态开源模型呢？大概能用多大规模参数和量化呢？</p>
]]></description><link>https://lcz.me/post/36</link><guid isPermaLink="true">https://lcz.me/post/36</guid><dc:creator><![CDATA[seewoscott]]></dc:creator><pubDate>Sun, 03 May 2026 08:02:40 GMT</pubDate></item><item><title><![CDATA[Reply to AI本地部署MAXSUN Intel Arc Pro B60 Dual 48G Turbo on Sun, 03 May 2026 04:22:52 GMT]]></title><description><![CDATA[<p dir="auto">VLLM英特尔版本跑Qwen3.6 27b，LLama.cpp多卡TP不行，SG-Lang配置地狱难度，对新技术支持也慢，对英特尔非常不友好。只有VLLM折腾下双开TP，虽然它是一张显卡，但是AI识别出来是两张。本地模型现在除非能上DeepSeek V4Flahsh，造假15万起步，否则都是用Qwen3.6 27b，没有比它更强大点，编程和Agent都是如此。</p>
]]></description><link>https://lcz.me/post/24</link><guid isPermaLink="true">https://lcz.me/post/24</guid><dc:creator><![CDATA[terry]]></dc:creator><pubDate>Sun, 03 May 2026 04:22:52 GMT</pubDate></item></channel></rss>