[hellohello2]

"Have you personally used any of the latest batch of even smaller local models?"

No I have not, which is why I asked (it wasn't a rhetorical question). Do you have pointers on what the recent improvements are?

[blurbleblurble]

Try qwen 3.6 models with hermes and see for yourself. 27b is excellent and 35b is very good for basic agentic tasks.