<?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[RSS Feed]]></title><description><![CDATA[RSS Feed]]></description><link>http://direct.ecency.com</link><image><url>http://direct.ecency.com/logo512.png</url><title>RSS Feed</title><link>http://direct.ecency.com</link></image><generator>RSS for Node</generator><lastBuildDate>Tue, 21 Apr 2026 00:58:21 GMT</lastBuildDate><atom:link href="http://direct.ecency.com/created/qwen/rss.xml" rel="self" type="application/rss+xml"/><item><title><![CDATA[My Progress wih Local AI - Qwen3.5 Models Impressed Me]]></title><description><![CDATA[Qwen3.5 is Alibaba's latest series of LLM models. They first released the large versions, Qwen3.5-397-A17B and Qwen3.5-122B-A10B then they released the medium versions Qwen3.5-35B-A3B and Qwen3.5-27B and]]></description><link>http://direct.ecency.com/hive-163521/@ahmadmanga/my-progress-wih-local-ai-qwen3-5-models-impressed-me-mmnng8by47d0108f</link><guid isPermaLink="true">http://direct.ecency.com/hive-163521/@ahmadmanga/my-progress-wih-local-ai-qwen3-5-models-impressed-me-mmnng8by47d0108f</guid><category><![CDATA[hive-163521]]></category><dc:creator><![CDATA[ahmadmanga]]></dc:creator><pubDate>Thu, 12 Mar 2026 15:55:36 GMT</pubDate><enclosure url="https://images.ecency.com/p/qjrE4yyfw5pJD9LKQ1BG3BAmr5TYaANmrJEBZ9YLQpdezGHuAo6SiRg3u7UYdHWCPczCCedomCRrhQ29Gn2qt2wWDLBx3gjWgLKrErqL62G94zPxL8jAdKrM?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Here is what Qwen 3.5 still cannot answer, still struggles with C64 coding skills. Full transcript (Qwen3.5-35B-A3B)]]></title><description><![CDATA[Habe die neuen Qwen 3.5 Modelle getestet, zumindest die, die ich lokal auf meinem PC ausführen kann wie das Qwen3.5-35B-A3B, ein Mixture of Experts Modell mit 3 Milliarden aktiven Parametern. Schaffe mit]]></description><link>http://direct.ecency.com/hive-163521/@vikisecrets/here-is-what-qwen-35-still-cannot-answer-still-struggles-with-c64-coding-skills-full-transcript-qwen35-35b-a3b</link><guid isPermaLink="true">http://direct.ecency.com/hive-163521/@vikisecrets/here-is-what-qwen-35-still-cannot-answer-still-struggles-with-c64-coding-skills-full-transcript-qwen35-35b-a3b</guid><category><![CDATA[hive-163521]]></category><dc:creator><![CDATA[vikisecrets]]></dc:creator><pubDate>Wed, 11 Mar 2026 10:54:00 GMT</pubDate><enclosure url="https://images.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4XiwVQYc85wQgScYKKUEZx7XaDS9Hfu8CkPbAfX3gFa84D36KzHM8KPee7UvRVG6VNJddFbbWAiXbHZHNUhtbBKCJnNKXAvHG6ArRSYJaWoFAjAD3U?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Qwen 3.5 ]]></title><description><![CDATA[Qwen 3.5 was releases 3 days ago. The model is pretty good for Tier 2 tasks below claude or another strong model. I wanted to upload a video but it doesnt work. Small Ollama models are: ollama run qwen3.5:9b]]></description><link>http://direct.ecency.com/qwen/@terryjobs/qwen-3-5</link><guid isPermaLink="true">http://direct.ecency.com/qwen/@terryjobs/qwen-3-5</guid><category><![CDATA[qwen]]></category><dc:creator><![CDATA[terryjobs]]></dc:creator><pubDate>Thu, 05 Mar 2026 18:22:39 GMT</pubDate></item><item><title><![CDATA[Happy holidays to everyone. ...]]></title><description><![CDATA[... #nativity The image was created with #Qwen , video with #klingai]]></description><link>http://direct.ecency.com/hive-193084/@gianmarcobarel/ukup9cdwu3jep3o9ys86nb</link><guid isPermaLink="true">http://direct.ecency.com/hive-193084/@gianmarcobarel/ukup9cdwu3jep3o9ys86nb</guid><category><![CDATA[hive-193084]]></category><dc:creator><![CDATA[gianmarcobarel]]></dc:creator><pubDate>Thu, 25 Dec 2025 09:02:45 GMT</pubDate></item><item><title><![CDATA[AI·Joe V11.3更新， 增加GPT-5.2和通义千问Qwen-Image]]></title><description><![CDATA[主要更新 增加GPT-5.2和通义千问 Qwen-Image图像模型。 OpenAI GPT-5.2 GPT-5.2是GPT-5系列中最新的前沿级模型，相比GPT-5.1具备更强的智能体性能和长上下文处理能力。它采用自适应推理机制动态分配计算资源，既能快速响应简单查询，又能为复杂任务投入更深层的处理能力。]]></description><link>http://direct.ecency.com/hive-105017/@lemooljiang/39k8gm122</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@lemooljiang/39k8gm122</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[lemooljiang]]></dc:creator><pubDate>Sun, 14 Dec 2025 11:55:42 GMT</pubDate><enclosure url="https://images.ecency.com/p/eAyTuXc4toTW1nA32v4xK89776gwb4SjnYCqKbjrxvdLHE8hNyxxV62oyn6qxmxoYjDycMmCz8N?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[AI·Joe V11.2更新， 增加DeepSeek V3.2，Qwen，GPT-5.1和Gemini 3 Pro]]></title><description><![CDATA[主要更新 增加DeepSeek V3.2，Qwen，GPT-5.1和Gemini 3 Pro等大模型。 DeepSeek V3.2 这是一个实验性（Experimental）的版本。作为迈向新一代架构的中间步骤，V3.2-Exp 在 V3.1-Terminus 的基础上引入了 DeepSeek Sparse Attention（一种稀疏注意力机制）， 针对长文本的训练和推理效率进行了探索性的优化和验证。]]></description><link>http://direct.ecency.com/hive-105017/@lemooljiang/4xr4pnrdn</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@lemooljiang/4xr4pnrdn</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[lemooljiang]]></dc:creator><pubDate>Mon, 24 Nov 2025 09:23:48 GMT</pubDate><enclosure url="https://images.ecency.com/p/eAyTuXc4toTW1nA32v4xK89776gwb4SjnYCqKbjrxvdLHE8hNyxxV62oyn6qxmxoYjDycMmCz8N?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[QWEN CLI vs Gemini : Which CLI AI Model is Better?]]></title><description><![CDATA[In my past posts, one of the user from Hive asked me to sooner or later switch to the CLI. And turns out the suggestion has worked out. The way CLI has improved my usage pattern and also the habit has]]></description><link>http://direct.ecency.com/hive-125125/@datastat/qwen-cli-vs-gemini-which</link><guid isPermaLink="true">http://direct.ecency.com/hive-125125/@datastat/qwen-cli-vs-gemini-which</guid><category><![CDATA[hive-125125]]></category><dc:creator><![CDATA[datastat]]></dc:creator><pubDate>Sun, 24 Aug 2025 14:20:24 GMT</pubDate><enclosure url="https://images.ecency.com/p/PB8ro82ZpZP35bVGjGoE8x7YLjV9UWTvRS3x5NFPGmxXetQEnQ38GvPWYvmCSGB7wiAHhAuMXYGSkUiGcb83QdS8HtVUCPZRfEUBxuWezvYbmnNr?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[QWEN CLI: Free 2K Run for Developers for Desktop CLI Usage]]></title><description><![CDATA[Every AI company is launching it's own CLI version of the interface. This way they want to add more competitive developer workflows. Some like IDE, Some like CLI and some prefer the API version through]]></description><link>http://direct.ecency.com/hive-125125/@datastat/qwen-cli-free-2k-run</link><guid isPermaLink="true">http://direct.ecency.com/hive-125125/@datastat/qwen-cli-free-2k-run</guid><category><![CDATA[hive-125125]]></category><dc:creator><![CDATA[datastat]]></dc:creator><pubDate>Sun, 10 Aug 2025 13:44:36 GMT</pubDate><enclosure url="https://images.ecency.com/p/C3TZR1g81UNbFzApDTmvFYJczLb7FJz3TaMfBugizPHodM5bncyYZbYsN1mt5tFWXXzpHyAkjLWnwEasgzuBLeXigQnCnigfxLWTSMjQTXTbbDF2ajiciRk?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[AI·Joe V8.5更新，更新DeepSeek R1模型]]></title><description><![CDATA[主要更新 AI·Joe此次更新DeepSeek R1 Distill Qwen 32B。删除了OpenAI的大部分模型，只有GPT-3.5 Turbo可用。 中美AI对抗越发激烈，相互拉黑和屏蔽。国内开发者已无法再调用OpenAI API, 每次请求都会发生一个unsupported_country_region_territory的错误！ DeepSeek R1 Distill Qwen 32B]]></description><link>http://direct.ecency.com/hive-105017/@lemooljiang/m472qpql</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@lemooljiang/m472qpql</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[lemooljiang]]></dc:creator><pubDate>Fri, 07 Feb 2025 10:22:30 GMT</pubDate><enclosure url="https://images.ecency.com/p/7ohP4GDMGPrUMp8dW718tJBTEaJiCZqta5CwEEUk2ZRyg5Muw8tKQqbKJigHVtYqd5DbAeMo7Aup72AWXv6nNwRdH5tkLpVvTd5k?format=match&amp;mode=fit" length="0" type="false"/></item></channel></rss>