Omar Shabab

Machine learning engineer in Singapore. I build AI tools, CLI applications, and civic tech, and write about the parts that were harder than they should have been.

06
Benchmark July 2026

The two numbers that decide local LLMs: 100 tokens/sec and 1M context

I ran a 754B model on a 512GB Mac Studio. It fits, it crawls, and its 1M context flag is a warning message and a silent cap. Where local models fail as coding tools, and the one job they are great at.

Read post
05
Hardware July 2026

Making a Logitech mouse follow its keyboard across Macs

Easy-Switch moves the keyboard and abandons the mouse. One HID++ packet fixes that, once you get past the two permission gates macOS hides between you and your own devices.

Read post
04
Claude Code June 2026

How I run Claude Code: Opus 4.8 advisor + ultracode

Two switches I leave on: the advisor tool and /effort ultracode. An honest, log-backed account of where they help, where they are overkill, and where the model wisely skips them.

Read post
03
Template April 2026

I built a SaaS starter because every other one is wrong

An opinionated Cloudflare-first template. Next.js 16, D1, Better Auth, Stripe. No monorepo. No edge-runtime religion. No status page.

Read post
02
Benchmark April 2026

Local LLM Benchmark: Gemma 4 vs Qwen 3.5

Head-to-head on a Mac Studio M3. 26 prompts, 6 categories, and one surprising finding about thinking mode overhead.

Read post
01
Data January 2026

Bangladesh 2026 National Election Candidates

Explore 1,680 candidates across 275 constituencies. Filter by coalition, division, party, and more.

Explore data