Doing LLM assisted programming using Qwen3.6-27B on dual R9700s on CachyOS
In this video I walk through a quick end to end example of getting dual R9700 GPUs working using opencode and Qwen3.6-27B
▶︎
Running a 118B Model on 12GB VRAM. Better Qwen 35B?
▶︎
TypeScript 7 Is Here (And It's 10× Faster)
▶︎
AMD Says 2 Ryzen AI Halos Can Run a 400B Model... I Tested It
▶︎
Nobody Explained Maxwell's Equations Like THIS!
▶︎
005: Auditing Codebases, Indeterministic LLM behaviour, and a new Audit feature in Haruspex
▶︎
OpenAI: A Bubble Bigger Than Dotcom
▶︎
I Have 128GB for Local AI... and This Is Crazy
▶︎
About my dual R9700 build - why I did what I did and what worked and what didn't.
▶︎
Making AMD's Ryzen AI Halo Do Work
▶︎
Laguna XS 2.1 33B A3B tested vs Qwen 35B A3B - 16GB Local LLM setup
▶︎
I FULLY Switched to Linux... but will I stay?
▶︎
My Favorite AI MCP Servers for the Home Lab in 2026
▶︎
This Tiny Engine Runs Impossibly Big AI Models Locally! (colibrì)
▶︎
The AI Crash & Why Tech Is Getting So Expensive...
▶︎
Running a 35B AI Model on 6GB VRAM, FAST (llama.cpp Guide)
▶︎
Citizen's Benefits & Rents: Who’s Cashing In on Billions from the State? - MONITOR
▶︎
Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026
▶︎
Germany is now a surveillance state
▶︎
The Rogue AI Story Just Got A Lot Worse (OpenAI Freaking Out)
▶︎