Local LLM on The Photonsphere https://photonsphere.org/series/local-llm/ Recent content in Local LLM on The Photonsphere Hugo -- gohugo.io en website@photonsphere.org (Mari Donkers) website@photonsphere.org (Mari Donkers) Mari Donkers / Wikimedia Commons Wed, 14 Oct 2026 00:00:00 +0000 Agentic coding on a laptop with Pi and a local LLM https://photonsphere.org/post/2026-10-14-pi-coder-local-llm/ Wed, 14 Oct 2026 00:00:00 +0000 website@photonsphere.org (Mari Donkers) https://photonsphere.org/post/2026-10-14-pi-coder-local-llm/ <p>On my AMD Ryzen AI 9 HX 370 laptop, which has a Radeon 890M iGPU — unified memory — I switched to using a local LLM for development, replacing the cloud models I'd normally reach for. The lean <a href="https://pi.dev">Pi coding agent</a> is also essential for this to work. If you've been wondering whether a local model can really do the job of building a big application, here's what I found.</p> <h1 id="the-setup">The setup</h1> <p>The project I am working on is a distributed communication system, split into two <a href="https://rust-lang.org/">Rust</a> codebases:</p>