<?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>Tool-Calling on Pavel Nasovich's Blog</title><link>https://forcewake.me/tags/tool-calling/</link><description>Recent content in Tool-Calling on Pavel Nasovich's Blog</description><generator>Hugo -- 0.157.0</generator><language>en-us</language><copyright>Copyright 2026</copyright><lastBuildDate>Sat, 09 Aug 2025 00:31:26 +0200</lastBuildDate><atom:link href="https://forcewake.me/tags/tool-calling/index.xml" rel="self" type="application/rss+xml"/><item><title>II-Search-4B: A Love Letter to Small Models (Or How I Learned to Stop Worrying and Embrace 4B Parameters)</title><link>https://forcewake.me/ii-search-4b-a-love-letter-to-small-models-or-how-i-learned-to-stop-worrying-and-embrace-4b-parameters/</link><pubDate>Fri, 08 Aug 2025 00:00:00 +0000</pubDate><guid>https://forcewake.me/ii-search-4b-a-love-letter-to-small-models-or-how-i-learned-to-stop-worrying-and-embrace-4b-parameters/</guid><description>A technical analysis of II-Search-4B reveals how this 4-billion parameter model achieves 91.8% SimpleQA accuracy through specialized web search capabilities, outperforming base models by 256% on multi-hop reasoning tasks. We dissect the practical deployment strategies from 8-GPU tensor parallelism to single-GPU quantization and Apple Silicon optimization, demonstrating how focused specialization enables frontier search performance at 1/50th the parameter count of comparable general-purpose models—proving that intelligent constraints and targeted training trump raw scale in the evolving landscape of AI agents.</description></item></channel></rss>