My llama.cpp Settings for Qwen3.8 27B
How I run a 27B quantized Qwen model locally with llama.cpp on modest hardware
Posts
A word on AI
I feel like I've become a good end user of AI models and here are my thoughts
Moving from WordPress to Zola
Why I moved my personal blog away from WordPress to Zola and what I learned along the way.
Switching to Credit Arbitrage
For years I've used a simple current account to pay my outgoings. This seems to mainly be the done thing, my salary goes in, I move some out to m...
Constraining an LLM in 16x2
I've re-created something I saw online a while back, I can't find the original but someone had given an LLM a prompt and basically let it loose i...
Devices No Longer Trust Their Owners
I am noticing an increasing trend in my online life where I am required to use devices and applications that must report a secure environment for the...
How to Disable Auto Play on Alexa
Follow the screenshots below to disable playing the next song on Spotify on Alexa. Although I use Spotify it may work with other services connect...
Monitoring CO2 levels with the ESP8266 NodeMCU V2 and the SCD41
When working from home I was curious about the air quality of the environment I was putting myself through for many hours of the day. I know the room...
My Experience Getting An Apicoectomy
During a check-up with my dentist I asked an innocent question about a spot on my gums just above a tooth in my mouth (which through some quick googl...
Using Aggressive Caching in WordPress
Using WordPress/Cloudflare I wanted my website webserver to be hit as infrequently as possible and have most of the traffic that visits my site hit C...