Well, I found how to use all my (unified) RAM, at last. Yes that's ollama running two models (Qwen3.6 (21GB) and llama3.3 (42GB)), pi-dev and opencode. And gues
A user shared their experience running multiple AI models, including Qwen3.6 and Llama 3.3, simultaneously using Ollama on their system. Despite successfully utilizing their RAM, the user noted that the setup still struggled with a specific coding task, failing to generate a requested Python script for gamma-ray spectra analysis and incorrectly claiming its presence. AI
