Running a 125 Billion Parameter AI with 32GB RAM and an RTX 3060

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

I ran 56 automated processes in six months, and the part that took the most time was the 'conditions for not notifying' — I'm revealing everything I did in those six months

Hello, I'm Pipimaru, a former engineer. During the day, I work on DX promotion at a medical institution, and when I get home, I build AI automations for myself.When I open X, it sometimes pops up.“I t ...