I finally bit the bullet and upgraded the graphics card to try and eek out a bit more performance on AI projects.
Badges
Badges come from GitHub once the author claims this feed.
Recent posts
every link opens the author’s post-
Upgraded the RTX 3060 to an RTX 5060 TI OC
-
Using those idle PC cycle for AI – one simple approach
Anyone experimenting with local AI models quickly learns that VRAM doesn’t share well.
-
Benchmarking LLMs — there is a better way
I’ve been writing some posts about some simple benchmarking of LLMs that I was doing after downloading various models, to understand how well they were working in my environment.
-
Hermes Agent vs. Pi Coding Agent: You don’t need to choose one over the other
I was asked about Hermes-agent vs. Pi and why I was looking at just one of them.
-
Update on using Strata on my home computer
A few weeks back I wrote a post about experimenting with running Qwen3.8-Flash-Next on my home computer.
-
Halloween themed kit from Printkits
I mentioned a while back that I had a subscription to Printkits.
-
An electronic football game I created
I have been applying my 3D printing and electronics skills to a little project in preparation for Thanksgiving.
-
Running Qwen3.8-Flash-Next on a 12GB VRAM Windows PC
My home machine is a rather modest 64GB RAM and a RTX 3060 with 12 GB VRAM, and based on memory prices it is not going to be upgraded any time soon.
-
A funny thing happened while using Hermes
I had several hours to kill while waiting on my wife to get her infusion the other day.