Running a local LLM with two GPUs
Let's perform surgery on two old systems to combine them into one AI powerhouse, capable of running our local LLM quite well! We'll show how to set up llama.cpp to support multiple GPUs in the same system, and show a couple of ways to take advantage of our new combined VRAM pool. 00:00 Intro 02:47 Surgery results 03:30 Building llama.cpp 05:13 First test 07:02 Two models at once 09:13 Summary 09:42 Outro

▶︎
Automating image tagging with a local LLM

▶︎
192GB of VRAM in One PC… The Cheap Way

▶︎
Setting up context in a local LLM

▶︎
Are prices getting better? GPU / RAM / SSD Price Watch - July 2026

▶︎
Configuring OpenCode for a local LLM

▶︎
‘AI code is insane trash’ | David Gerard

▶︎
AI stole Intel’s gaming GPU from us - Intel ARC B70

▶︎
Running a 35B AI Model on 6GB VRAM, FAST (llama.cpp Guide)

▶︎
The Linux Kernel is Falling Apart.

▶︎
DO NOT BUY: LG’s Spyware TVs, Monitors, and Wiretapping Concerns

▶︎
ThinkingCap Qwen 3.6 27B MTP benchmarked vs Base Qwen 27B - 16GB Local LLM setup

▶︎
It's Official, The AI Bubble Just Popped (Here's Why)

▶︎
I Bought an RTX 5090 to Run AI Locally — Here's Why

▶︎
Trump Speech CANCELLED over Shock BACKFIRE

▶︎
Bonsai 27B Runs Qwen 3.6 27B at 10x less memory.

▶︎
Building agents and skills with OpenCode

▶︎
NVIDA's New DGX Stations Destroying The Entire AI INDUSRTY!

▶︎
Building llama.cpp from source

▶︎
Official SteamOS vs Bazzite… Which one is better?

▶︎
