selicos’s local AI setup

A 128 GB Strix Halo machine, local models and practical infrastructure work.

Why this example exists

Because selicos would have had to connect via MCP or sign in and create it manually in Markdown, they asked: how about being able to post a summary of their setup instead of plugging their credentials and tools into a third-party site? So here it is.

My local setup

Strix HALO 128gb - Framework mainboard in a custom SFF PC. Just moved from Ubuntu to Fedora 44. Using: LM Studio (primary), Lemonade, not yet got into vLLM and llama.cpp directyly after moving to Fedora. Running Gemma e4b, Gemma 4 26b a4b IT, Qen 3.6 35b a3b, and Qwen 3.8 27B. I want to get Qwen 3.8 Next or similar large models working but have to dedicate the system to that vs running services and smaller models for them.

Apps & agents

Subwave is all I'm actively running against the local LLMs, but I have vscode connected through a few extensions and chat tools (I've added LM Studio to Copilot Chat but it likes to use cloud models and burn tokens sometimes). I've also set up pi, Openhands, and a few other tools but haven't had a project to work on with them.

What I'm building

I built an app to track and move PC parts I own between systems, partially to build a better LLM server. The next hardware goal is adding a 3060 12gb for inference, or what can be run on that vs in system memory on the Strix Halo. That will need a dock or small PCIe extension cable.

AI at work

My employer has us using Copilot a lot, and it works well enough if you are efficient or set up already. I do infra not development and local models are seemingly enough for most asks like automation scripting.