Ming-3.0-tts-0.5B peaked at 2.9 GB and ran at about 0.65x real time. The Python decode loop sets the pace, not the card. What to measure first.
Ming-3.0-tts on a 16 GB card: the GPU sat mostly idle, and why a bigger one barely helps
Related
I review my AI agent's code like a merge request
These days most of the code in my side projects is written by Claude Code. I describe what I want, it...
Claude for business: testing three Claude models as SQL agents on a CRM
Claude for business decisions often come down to which model to put behind an agent, and this post...
The verified agent pattern: building outbound agents for a web that blocks them by default
From September, agent-class traffic is blocked by default on a large share of the commercial web. An agent that browses anonymously and hopes for...