JustFoura

Llama Studio V3

A Windows 11/Linux compatible GUI for Llama.cpp and vLLM using Tauri v2. Rust-based. Efficient display.

Why I did this: To provide myself with an easy-to-use GUI for llama.cpp without having to go into the terminal.

What I learnt from it: Tauri applications. llama.cpp. Local model inference.

Wplace Leaderbot

A Python-based bot to gather daily, weekly, monthly, or all-time information for specific configured zones within Wplace.live and display them either on a daily-based timer or on command into Discord via a Discord bot.

Why I did this: To set up an easy automated display of leaderboard scores in specific zones.

What I learnt from it: Discord bot integration. Python. Public information scraping.

Genxe Game Engine

A Rust/C# based game engine.

Why I did this: To create easy games using AI-MCP integration.

What I learnt from it: To Be Determined

Llama Studio V2

Llama Studio V1

Xenite

A custom AI coding harness, built into a GUI app and a CLI.

Why I did this: To create games and coding projects easier.

What I learnt from it: AI-integration. Electron desktop applications. Coding harnesses.

Tranquility Code

A full TUI AI coding harness built on top of PI coding agent.

Why I did this: To code internally easier using custom trained LLMs.

What I learnt from it: Rust-based TUI. TUIs. Coding harnesses.

Which AI do I use

Depends, I found GLM-5.3 Flash to be very good at local model optimizations--while GPT-5.6 (or 6) Luna to be good at coding.

Do I have a job

No lmao

Any form of AI / coding education

Nope, either self-taught or I let AI take care of it.

Any AI subscriptions

Currently GPT Plus and GLM Coding Plan Lite. But it is subject to change depending on the latest AI landscape.

Image gen?

I tend to avoid image generation, but for the occasional specific, wallpaper, emoji--I might.

Operating System

Windows 11 mainly, sometimes Linux since it has exclusive support for certain applications (such as SGLang or vLLM) but I find Linux to be VERY unstable--otherwise productivity may be higher.

Hardware

RX-9060-XT 16GB. Ryzen 7 5800x paired with 16GB DDR4 system RAM.

Local Models

Qwen3.8 27B fits nicely at ~3-4 BPW, it's a little slow but it works. Qwen3.6 35B A3B (specifically LuffyTheFox's version) is good for other applications. Currently trialing Qwen3.8 Flash Next.

Do I think AI is good

Very good nowadays--but it requires specific set up and use, otherwise I believe a good developer with AI can get work up to 2-5x faster. Also, nowadays you don't even need coding knowledge to use AI to code -- latest models like Opus 5.5 or GPT-6 Astra are very good (or even on the low end--models like GPT-6 Luna and Sonnet 5.5 are very good)