Measured 11 local LLM configurations. llama.cpp was too slow for Qwen3.8-Flash-Next, but with Strata and an NVMe SSD, it has ...

This March, I wrote, “I want something I can lose myself in, forgetting to eat or sleep.” Seven months later, my desires had taken on a much clearer form.Yes, money.I thought I’d use ChatGPT to ...