New here?
Create an account to submit posts, participate in discussions and chat with people.
Sign up
27
posted 1 year ago by ProductConnoisseur on scored.co (+0 / -0 / +27Score on mirror )
You are viewing a single comment's thread. View all
ProductConnoisseur on scored.co
1 year ago 1 point (+0 / -0 / +1Score on mirror ) 1 child
You should look into uncensored locally-run models if you haven't already. You'll want at least 8GB VRAM.

Grab LM Studio and use the search function (on the left) to look up and download uncensored models. I recommend trying Lexi LLama 3.1 8B uncensored Q8.
JoePutin on scored.co
1 year ago 0 points (+0 / -0 ) 1 child
How quick are the responses. I tried a year or so ago and it was brutally slow. (Albeit probably didnt do a good job if setup)
ProductConnoisseur on scored.co
1 year ago 0 points (+0 / -0 )
Depends a lot on your hardware. I have a pretty old GPU (GTX 10xx series 8GB) and it's not too bad. You can try a more heavily quantized version (Q5 or Q4) which are smaller and faster, with the trade off being lower quality responses.
Toast message