Topic
0 news articles · 4 tutorials
I installed Claude Code on a stock Ubuntu 24.04 box, set up Pro OAuth, and shipped a real refactor with it. This is the install that worked, including the bits the official docs skip.
Llama.cpp is the minimal inference engine that runs on anything. I built it from source on Mac and Linux. This is the build that worked, with the GPU flags that mattered.
I ran Gemma 4 9B locally on a 32GB Linux box for a week of normal use. This is the Ollama install, the model variants worth pulling, and the one config tweak the docs do not flag.
Zed is the fastest editor I have used on Linux, with native AI chat and inline-edit. This is the install I run, including the Wayland fix that the docs do not flag.