<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Models on Radar · Local AI &amp; Agent Security</title><link>https://radar.clouddomus.com/categories/models/</link><description>Recent content in Models on Radar · Local AI &amp; Agent Security</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 18 Nov 2026 07:00:00 -0300</lastBuildDate><atom:link href="https://radar.clouddomus.com/categories/models/index.xml" rel="self" type="application/rss+xml"/><item><title>Qwen4: no weights yet, but signs of a 27B (and maybe a 35B) are getting stronger</title><link>https://radar.clouddomus.com/news/2026-11/qwen4-signals/</link><pubDate>Wed, 18 Nov 2026 07:00:00 -0300</pubDate><guid>https://radar.clouddomus.com/news/2026-11/qwen4-signals/</guid><description>Qwen4-Max is still API-only. Huawei published Qwen4-27B quants and a Qwen team lead hinted at smaller models.</description></item><item><title>Hy4 Flash goes open-weight: 224B (12B active), 1M context and an official GGUF</title><link>https://radar.clouddomus.com/news/2026-11/hy4-flash-open-weights/</link><pubDate>Wed, 18 Nov 2026 01:40:00 -0300</pubDate><guid>https://radar.clouddomus.com/news/2026-11/hy4-flash-open-weights/</guid><description>Tencent opened Hy4 Flash, its FP8 build and the Base model. Official GGUF from 126 to 157 GiB; the 59 GiB Engram table can live in RAM or on NVMe. Custom license.</description></item></channel></rss>