gpt-oss:20b if you can run it, it's pretty good
You would use a RAG for augmenting the local model, I'll experiment with that soon
Discussion
Thx for your reply! 20B is a bit high for my current experimenting laptop, but I‘ll check it out asap once I‘ve upgraded my HW.
Would be interested to hear about your experience & results with augmenting the model. Pls share if possible 🙏🏼