Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!


New on LowEndTalk? Please Register and read our Community Rules.

All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.

LLM (deepseek?) on KimSufi server

12346»

Comments

  • seenuseenu Member

    for the amount you pay for vps/server, you can pay less to deepseek api n have results damn faster, imho.

    i went through this rabbithole n not gonna do it again, better to pay for apis.

  • NeoonNeoon Community Contributor, Veteran
    edited May 3

    @jugganuts said:
    so not usable irl :(

    128B dense, pretty fat, you can't even run that with a 96GB GPU.
    A quant might fit, however its not gonna be fast either.

Sign In or Register to comment.