Local AI & Self-Hosted LLMs

Three and a Half Weeks, 689M Tokens, No Meter featured image

Three and a Half Weeks, 689M Tokens, No Meter

689M tokens. 25 days. ~$40 electricity. The math, the caveats, and what changed when the meter stopped existing.

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more
Qwen3.8 27B on Dual RTX 3090s: A vLLM Field Report featured image

Qwen3.8 27B on Dual RTX 3090s: A vLLM Field Report

Three days into making Qwen3.8 27B my daily local coding driver on dual 3090s — the hybrid linear-attention architecture, an OOM that masqueraded as a backend error, and what the …

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more
How I Bridged CLI AI Agents to Apple's Walled Garden featured image

How I Bridged CLI AI Agents to Apple's Walled Garden

Apple apps are locked down with no APIs, but SQLite local databases and AppleScript let CLI AI agents bridge Reminders, Notes, Calendar, Mail and more — no cloud, no API keys, just …

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more
Self Hosted AI: Actually Running Local LLMs for a Multi-User Household featured image

Self Hosted AI: Actually Running Local LLMs for a Multi-User Household

How self-hosted AI became the final piece of my homelab puzzle, delivering true parallel processing for multi-user setups and unlocking the real superpower of knowledge management.

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more
Running Qwen3.6 27B Locally on Dual RTX 3090s with vLLM v0.19 featured image

Running Qwen3.6 27B Locally on Dual RTX 3090s with vLLM v0.19

How I went from a blank Docker template to 116+ tok/s with speculative decoding, FlashInfer, and a 160k context window on dual 3090s.

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more
Qwen3.5 Showdown: 27B Q8 vs 35B-A3B Q8 — Real-World Testing for Local AI featured image

Qwen3.5 Showdown: 27B Q8 vs 35B-A3B Q8 — Real-World Testing for Local AI

A real-world comparison of Qwen3.5 27B Q8 and 35B-A3B Q8 running locally on a dual RTX 3090 homelab — which one actually belongs in your daily workflow?

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more
One Year Later: The Agentic CLI Revolution Revisited featured image

One Year Later: The Agentic CLI Revolution Revisited

A year ago, I predicted CLI AI tools would transform development. Here's what actually happened—the good, the unexpected, and the 'wait, what?' moments.

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more
From Google Skills to AI Skills: The Evolution of Information Discovery featured image

From Google Skills to AI Skills: The Evolution of Information Discovery

The art of crafting perfect search queries has evolved into the skill of prompt engineering. Learn how mastering AI interactions is the next generation of being a master Googler.

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more
AI's Hidden Vulnerability: The Rising Threat of Prompt Injection Attacks featured image

AI's Hidden Vulnerability: The Rising Threat of Prompt Injection Attacks

How adversaries manipulate AI by embedding instructions into data sources and what defenders must do to respond.

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more
Don't Get Left Behind: Evolve in this AI Era featured image

Don't Get Left Behind: Evolve in this AI Era

Adapt and thrive in the AI era by enhancing strategic skills, ownership, and creativity to stay ahead in software development

Derek Armstrong - Payments Engineer · AI · Infrastructure
Derek Armstrong
Read more

Showing 1-10 of 13 items (Page 1 of 2)