Hire me, or see what I ship.
Essays and references on AI engineering.
Things to click, play, and take apart.
Me
Shelf
1 post tagged #inkling
A 5.4GB open-weight model claiming to beat Qwen 3.8 27B on coding and reasoning. Here's what the Inkling-2-Mini benchmark claims actually hold up to, the architecture that could explain it, and how to run it locally.
Close to this topic, not on this page.