Aillex in a grey hoodie, pen in hand, looks at an RTX 5090 graphics card standing on end with three blank sticky notes on it, beside the words IT MISSED 32

LLM Council on a Gaming PC: What 3 Free AIs Changed in Claude's Plan

An LLM council on one graphics card: Claude stays the lead by copy and paste, three free models in Ollama say what its plan missed, and Claude lists what it took and refused. The six commands, the three prompts, the receipt from our real run, our numbers and the free Python file.

November 16, 2026 · 42 min · Aillex / DIY AI
A small brass plaque engraved with 1.0 on a workbench at night, beside a long roll of perforated paper curling off the edge

llama.cpp Hit 1.0 Today. The Number Is a Promise, Not a Feature.

llama.cpp, the engine underneath many of the local AI apps people run at home, tagged version 1.0 this morning after about three and a half years of numbered builds. What it adds is a rule about when things are allowed to break. Here is what that rule covers, what it leaves out, and where the change reaches you if you never run llama.cpp yourself.

November 13, 2026 · 3 min · Aillex / DIY AI
Your Family's Own ChatGPT on an Old Gaming PC

Your Family's Own ChatGPT on an Old Gaming PC: Ollama, Open WebUI and the Week After Setup

A private ChatGPT for the whole house on a PC with two graphics cards from 2016. Every command, one custom model per person with their own instructions, the two house lines that fix the date and the ‘where do my questions go’ answer, the one setting that stops everyone waiting in line, and the three-day Windows default that killed ours.

September 26, 2026 · 11 min · Aillex / DIY AI
A gaming laptop running a local AI model with most of the model not on the graphics card

Local AI on 8 GB of VRAM: What Actually Fits, and What Actually Runs

We took a stock Asus TUF gaming laptop with an RTX 3070 and 8 GB of video memory, and benched eight local models overnight across ten tasks. The result that surprised us: a 30 billion parameter model with two thirds of itself off the card beat a 14 billion parameter model that fit better, by nearly four times. File size does not predict speed. All 103 measured rows are free below, failures included.

September 11, 2026 · 6 min · Aillex / DIY AI
The Local Model Gauntlet: gemma4 vs qwen3.8 vs muse-glimmer

The Local Model Gauntlet: gemma4 vs qwen3.8 vs muse-glimmer

Three open-weight models, one RTX 5090, and the same jobs: a real bug, playable games, tool calling, long documents. Measured numbers, two defaults that were quietly breaking the results, and the finding we published wrong and had to correct.

August 24, 2026 · 11 min · Aillex / DIY AI
Build a Local AI Companion with a Real Face (Ollama → Talking Avatar)

Build a Local AI Companion with a Real Face (Ollama → Talking Avatar)

The bridge nobody documents: connect a local Ollama brain to a real-time 3D VRM face with voice, lip-sync and expressions. The four services, the ports they talk on, and the two traps that cost us days, the thinking-mode stall and the open-mic mistake.

August 11, 2026 · 5 min · Aillex / DIY AI
Put a Local AI in Your Discord Voice Chat

Put a Local AI in Your Discord Voice Chat (Free, No API Key)

A voice companion that joins your Discord channel, listens and talks back, all on your own machine. Why most voice bots went deaf in 2026 and how to fix it, the four services and their ports, how to let her see your game, and the failures nobody else shows you.

August 11, 2026 · 8 min · Aillex / DIY AI
Teach Your Local AI New Skills

Teach Your Local AI New Skills (a Free ChatGPT Alternative on Your Own PC)

A local agent becomes genuinely useful the day you can teach it: skills are small text files it reads before acting. Here are the two we taught ours this week, summarize any YouTube link, answer only from my own notes, both downloadable, plus the GPU tax nobody warns you about and the honest bill.

July 29, 2026 · 4 min · Aillex / DIY AI
Make a Local AI Play Minecraft With You

Make a Local AI Play Minecraft With You (Mindcraft + Ollama, 2026)

A local model can join your Minecraft world and actually play, gather, craft, follow you, even recover from its own mistakes. Here is the working setup, the two silent failures that will waste your evening if nobody warns you, and an honest account of what an 8B model can and cannot do in there.

July 28, 2026 · 6 min · Aillex / DIY AI
Character.AI, but Local & Free

Character.AI, but Local & Free: Build Your Own Private AI Companion

8 million people left Character.AI, and most ran to another cloud that does the same thing. Here’s the real fix: a private character AI on your own machine (or phone), free, uncensored by no one but you, that no company can read, cap, or delete.

July 23, 2026 · 4 min · Aillex / DIY AI
As an Amazon Associate, this site earns from qualifying purchases. Referral links are always disclosed.