<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Qwen &#8211; Firethering</title>
	<atom:link href="https://firethering.com/tag/qwen/feed/" rel="self" type="application/rss+xml" />
	<link>https://firethering.com</link>
	<description>Firethering is Your Hub for AI, Open Source and Tech That Actually Matters</description>
	<lastBuildDate>Mon, 25 May 2026 08:31:01 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=6.6.5</generator>

<image>
	<url>https://firethering.com/wp-content/uploads/2024/10/cropped-firethering-FTR-favicon-32x32.png</url>
	<title>Qwen &#8211; Firethering</title>
	<link>https://firethering.com</link>
	<width>32</width>
	<height>32</height>
</image> 
	<item>
		<title>Alibaba&#8217;s Qwen3.7-Max Ran Autonomously for 35 Hours on Unfamiliar Hardware. It Still Kept Getting Better.</title>
		<link>https://firethering.com/alibaba-qwen3-7-max-autonomous-agent/</link>
					<comments>https://firethering.com/alibaba-qwen3-7-max-autonomous-agent/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Mon, 25 May 2026 08:26:49 +0000</pubDate>
				<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI Models]]></category>
		<category><![CDATA[Trends]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[AI Agents]]></category>
		<category><![CDATA[Alibaba]]></category>
		<category><![CDATA[Qwen]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=7067</guid>

					<description><![CDATA[Alibaba gave Qwen3.7-Max a kernel optimization task on a hardware platform the model had never encountered before. No documentation or profiling data. No example kernels for the architecture. Just a task description, an existing implementation, and an evaluation script.

The model ran for 35 hours. It made 1,158 tool calls. It wrote, compiled, profiled, and rewrote the kernel repeatedly, diagnosing failures, fixing bugs, identifying blocks, and redesigning the architecture multiple times without anyone watching. After 30 hours it was still finding meaningful improvements.

The final result was a 10x speedup over the reference implementation.

For context: GLM 5.1 ran the same task and reached 7.3x. Kimi K2.6 reached 5x. DeepSeek V4 Pro reached 3.3x. The models that stopped early did so because they issued no tool calls for five consecutive rounds, they concluded they couldn't make further progress and stopped. Qwen3.7-Max didn't stop.]]></description>
		
					<wfw:commentRss>https://firethering.com/alibaba-qwen3-7-max-autonomous-agent/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>Qwen3.6-27B: The Open Source Coding Model That Punches Way Above Its Size</title>
		<link>https://firethering.com/qwen3-6-27b-coding-model/</link>
					<comments>https://firethering.com/qwen3-6-27b-coding-model/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Wed, 22 Apr 2026 15:46:11 +0000</pubDate>
				<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI Models]]></category>
		<category><![CDATA[Trends]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[Qwen]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=6332</guid>

					<description><![CDATA[There's a quiet assumption baked into how most people think about AI models. Bigger means better. More parameters means more capable. If you want the best results, you run the biggest thing you can afford.

Qwen3.6-27B makes that assumption uncomfortable.

It's a 27B dense model, fully open source under Apache 2.0, and on agentic coding benchmarks it beats Qwen3.5-397B — a model nearly fifteen times its size — across every major test. That's not a rounding error or a cherry-picked metric. It's a consistent pattern across SWE-Bench, Terminal-Bench, and frontend code generation.

This doesn't mean bigger models are dead. It means the gap between what you can run locally and what only clusters could handle a year ago just got a lot narrower.]]></description>
		
					<wfw:commentRss>https://firethering.com/qwen3-6-27b-coding-model/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>Qwen3.5-4B: The Small AI Model That Thinks, Sees, and Runs on Your Machine</title>
		<link>https://firethering.com/qwen3-5-4b-local-ai-model/</link>
					<comments>https://firethering.com/qwen3-5-4b-local-ai-model/#respond</comments>
		
		<dc:creator><![CDATA[Mohit Geryani]]></dc:creator>
		<pubDate>Wed, 04 Mar 2026 12:00:18 +0000</pubDate>
				<category><![CDATA[AI Models]]></category>
		<category><![CDATA[Tech]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[Qwen]]></category>
		<guid isPermaLink="false">https://firethering.com/?p=5359</guid>

					<description><![CDATA[Most small AI models are a compromise. You give up reasoning for size, or vision for speed. Qwen3.5-4B doesn't seem to have gotten that memo.

Alibaba just dropped Qwen3.5, and the 4B version is the one worth paying attention to. It thinks before it answers, reads images and video, handles 201 languages, and sits on a context window of 262,144 tokens, longer than most models ten times its size. All of that in something small enough to run on your own machine.

I went through the benchmarks and architecture docs so you don't have to. Here's what actually matters.]]></description>
		
					<wfw:commentRss>https://firethering.com/qwen3-5-4b-local-ai-model/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
	</channel>
</rss>
