Blog

AI, local LLMs, cloud architecture, and developer tools.

Gemma 4 26B on 24GB MacBook
NEW Featured

I Fixed the 26B: From 2/10 to My Daily Driver at 49 tok/s (Ollama Can't Do This)

From 2 tok/s to 49 tok/s. Ollama's 3 bugs, the missing Q3 quant, 128K context for free, Qwen 3.5 35B on 24GB, and a Claude Code clone running locally. Plus: computer use with bounding boxes.

Gemma 4 llama.cpp Unsloth localcoder Apr 5, 2026
Gemma 4 Benchmark
NEW Featured

I Tested Every Gemma 4 Model Locally on My MacBook -- What Actually Works

Audio ASR in 3 languages, image understanding, full-stack app generation, coding, and agentic behavior. E2B vs E4B vs 26B vs 31B on M4 Pro 24GB. Plus free cloud API benchmarks.

Gemma 4 Ollama Benchmark Local LLM Apr 3, 2026
Ralph Wiggum Technique

The Ralph Wiggum Technique: Autonomous AI Development with Claude Code

How a goat farmer's 5-line bash script changed AI-assisted coding forever. Run Claude Code in an infinite loop while you sleep.

Claude Code AI Coding Automation Jan 11, 2026
AI vs AI

The Ultimate AI Code Editor Showdown

Roocline vs Aider vs Windsurf vs Cursor vs GitHub Copilot. A comprehensive comparison based on real-world usage and community feedback.

AI Editors Comparison Dev Tools Mar 2, 2024
Coming Soon
Upcoming

Cloud Architecture Best Practices 2026

Serverless, multi-cloud strategies, and AI-powered infrastructure management.

Cloud Architecture