LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

submitted 1 year ago by Hyddro26@alien.top to c/localllama@poweruser.forum

38 comments fedilink hide all child comments

Looking for any model that can run with 20 GB VRAM. Thanks!

you are viewing a single comment's thread
view the rest of the comments

[–] Herr_Drosselmeyer@alien.top 1 points 1 year ago (2 children)

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.

[–] shaman-warrior@alien.top 1 points 1 year ago (1 children)

Do you know if 13b-8bit is better than 70b quantized?

[–] TuuNo_@alien.top 1 points 1 year ago