https://shadowcp.dev/series/running-local-ai-on-intel-lunar-lake/ Recent content in Running Local AI on Intel Lunar Lake on Rosen Papazov Hugo -- gohugo.io en <a href="https://creativecommons.org/licenses/by-nc/4.0/" target="_blank" rel="noopener">CC BY-NC 4.0</a> Mon, 06 Apr 2026 12:00:00 +0300 https://shadowcp.dev/posts/2026/04/running-local-ai-on-intel-lunar-lake-part-1-hardware-drivers-and-the-intel-compute-stack/ Mon, 06 Apr 2026 12:00:00 +0300 https://shadowcp.dev/posts/2026/04/running-local-ai-on-intel-lunar-lake-part-1-hardware-drivers-and-the-intel-compute-stack/ Part 1 of 4 in a series on building a fully local AI development environment on an Intel Core Ultra 7 268V laptop running Fedora 43. Why local AI? Cloud-hosted AI is convenient until it isn&rsquo;t. Latency spikes, privacy concerns with proprietary code, rate limits during crunch time, and the monthly bill that creeps up. Running models locally solves all of these — if your hardware can handle it. Intel&rsquo;s Lunar Lake processors are interesting for this.