Earlier quoted context omitted.
I find 35B A3B viable as well, but your harness and runtime really matters to get tool calling and such dialed in. In fact, I would encourage you to experiment with it some as I find I get more reliable output from 35B A3B, though 27B is still generally smarter. A3B with a review cycle or two from 27B is great for me. One of the reasons is, with good specs and design, A3B is just so fast. It isn't as smart as the 27B…
How do you do the review cycles? Is this some automated feature of your harness? Do you have a generic prompt for this or ask 27B yourself?
Usually something like dsv4 running them. Depends in the horizon. It’s kind of an overnight thing for the project. Use matt pocock skills or similar. Build good spec. Iterate on it with a big model or your brain. Break it down into pieces and features like you would for a human. Tell them to work on tickets. Have other agent review. Repeat. Stuff gets built. You can keep a smarter agent in a loop (think bash) to review and have a simple decision tree: implement, review, mark done, pick next ticket. When no tickets stop. If error or pathology detected, touch a stop file. That is what I run overnight. A3B likes a simple harness as does 27B, mostly unmodified Pi with a proxy to fix model bugs. It takes some investment. It isn’t batteries included. These small models are not very smart. They need a pretty narrow task domain.