For some people “uncensored” means it hasn’t been lobotomized, but for others it means it can write porn.

Wonder what card you have that’s 20GB?

That’s actually so funny, the 2 times I’ve asked this before, I get downvoted to shit.

What are you looking for?

With a 3090, you can run any 13b model in 8 bit, group size 128, act order true, at decent speed.

Go-tos for the more spicy stuff would be Mythomax and Tie fighter.

Best experience I had was with TheBloke/Wizard-Vicuna-30B- Uncensored-GGML

Best 30B llm so far in general. Censorship kill’s capabilities

I haven’t found one that is universally best regardless of the benchmarks. Same story with vector embeddings, you’ll need to test a few out for your own use case.

The best one I’ve found for my projects though is https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca and the AWQ implementation https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-AWQ.