Here’s my thought on qwen3
I really don’t know much about every self-hostable LLM out there… so much as happened. I am blessed at home with a pretty beefy GPU and so although I don’t know all the deets, I can run a lot of the reasonably large “open source” models. The one I’ve been playing with lately is qwen3. The conversational flow has felt more natural with it compared to llama3.2 or dolphin3. Granted I might need to update something and my experience is limited. I’ve also had good experience with gemma3 as a noteworthy contender for my go-to LLM right now in open-webui
Note
This is one of [[ my-thoughts ]]. I picked this up from Waylon Walker(https://thoughts.waylonwalker.com). It’s a short note that I make about someone else’s content online. Learn more about the process Thoughts