[outside1234]

Which local model works best for folks? Sort of intimidated by the large number of models on Hugging Face and it is hard to conceptualize which of the variants work the best.

I downloaded:

mistral-7b-v0.1.Q4_K_M.gguf Q4_K_M 4bits 4.37 GB 6.87 GB medium, balanced quality - recommended

Was that a good choice?

[stuartriffle]

Yes (imho) just be sure to get the instruct or chat model of any LLM you try. There is an awesome snapshot of what models people are using here:

https://openrouter.ai/rankings