Yeah Linux likes to fill the cache entirely. If you want it to do that less and performance isn’t a concern, set up something that drops the caches every few hours running this as root: echo 1 > /proc/sys/vm/drop_caches

I get good mileage out of the Jan client and Void editor, various models will work but Jan-4B tends to do OK, maybe a Meta-Llama model could do alright too. The Jan client has settings where you can start up a local OpenAI-compatible server, and Void can be configured to point to that localhost URL+port and specific models. If you want to go the extra mile for privacy and you’re on a Linux distro, install firejail from your package manager and run both Void and Jan inside the same namespace with outside networking disabled so it only can talk on localhost. E.g.: firejail --noprofile --net=none --name=nameGoesHere Jan and firejail --noprofile --net=none --join=nameGoesHere void, where one of them sets up the namespace (–name=) and the other one joins the namespace (–join=)