<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>DeepSeek V4-1 Flash on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/deepseek-v4-1-flash/</link><description>Recent content in DeepSeek V4-1 Flash on Negi AI Lab</description><image><title>Negi AI Lab</title><url>https://ai.negi-lab.com/images/og-default.png</url><link>https://ai.negi-lab.com/images/og-default.png</link></image><generator>Hugo -- 0.154.5</generator><language>ja</language><lastBuildDate>Sat, 12 Sep 2026 02:53:19 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/deepseek-v4-1-flash/index.xml" rel="self" type="application/rss+xml"/><item><title>DeepSeek V4-1 Flash 比較と選び方：ローカルLLM開発で失敗しないVRAM容量とハードウェア選定</title><link>https://ai.negi-lab.com/posts/deepseek-v4-1-flash-hardware-guide-rtx-vram/</link><pubDate>Sat, 12 Sep 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/deepseek-v4-1-flash-hardware-guide-rtx-vram/</guid><description>DeepSeek V4-1 Flashは「速度」と「マルチモーダル MoE」の両立。API利用なら最強コスパだが、ローカル環境ではMoE特有のパラメータサ...</description></item></channel></rss>