homelab · self-hosting · local AI
Things I build
on my own hardware.
I'm JR. I build software, games, AI systems and hardware at home, and this is where I show them. Everything here runs on a homelab, and the build log has the real numbers and the mistakes.
Projects
StarCraft native engine (sc-native)
A from-scratch native Linux engine for StarCraft. Installers for Ubuntu, Linux Mint and Debian compile it on your computer. No game data included: it reads your own StarCraft (Remastered) install.
The Long Rot
A realistic first-person, open-world zombie survival game from my studio, Tensor Games. The world didn't end in an hour. It rotted away over years.
Qwen: a self-hosted voice assistant
A voice-first assistant I run on my own hardware. It listens, thinks with a local language model, speaks back, and can use tools like search, notes, reminders and my homelab's status.
Blender and 3D AI tools
A set of Open WebUI tools that let a local AI model drive Blender, turn images into textured 3D models, and slice and run 3D prints on my Bambu P2S.
Fleet status
Latest posts
Llama 3.2 Vision Doesn't Run Here (And Here's Why)
Not every homelab post ends with a working setup. This one’s about a model that, as far as I can tell, cannot currently run on my hardware …
Five Models, One GTX 1060: A Laptop Local AI Bake-Off
Testing five small LLMs on an aging GTX 1060 laptop to find out which ones are actually usable — and which ones will make you question your life …
Getting this blog and its own email address live: a full night of self-inflicted problems
Registering a domain sounds like a five-minute task. Getting this actual blog live, plus a working self-hosted mailbox on that domain, took most of a …
Building out my gaming server on Linux Mint
Spent the last few weeks reworking the home lab, and this round was getting my gaming server fully set up — Steam library, storage layout, and …
Can a local model actually design something? gpt-oss:20b vs Gemma 4 12B
Wanted to see if either of my two resident models could act as an actual design collaborator — not just answer questions, but iterate on real critique …
Finding the Best Local LLM for a 16GB AMD GPU
If you’ve spent any time searching for “best local LLM for X GB VRAM,” you’ve probably noticed the same problem I ran into: …
Open WebUI: why I stopped trusting Knowledge Bases and just typed the facts into Memory
Spent a chunk of a weekend debugging something that turned out not to be a bug I could fix — it was a known limitation I had to route around instead. …
Three tests, one winner: what Gemma 4 got right that gpt-oss didn't
Didn’t set out to run a Google-vs-OpenAI bake-off. Just kept testing models on real tasks across two machines, and the pattern kept repeating …
Unresolved: intermittent response delays on the laptop, and everything I ruled out
Not every post here ends with an answer. This one’s a log of a bug I haven’t fixed yet, written down so the next session doesn’t …
Three Bugs Deep: Getting Open WebUI Running on My ASUS Laptop
I spent a night debugging what looked like a single broken Docker container on my ASUS laptop (i7-8750H, GTX 1060 6GB, Linux Mint). It turned out to …
Finding the Right Local AI Model for a 6GB Laptop GPU
My daily-driver laptop is an ASUS laptop — an i7-8750H with a GTX 1060 6GB, running Linux Mint. Not a beefy AI rig by any means, but with the right …