• Trimatrix
    link
    fedilink
    English
    arrow-up
    4
    ·
    8 days ago

    Check the UGI leader board on hugging face and select the highest ranking model your local GPU can run on a minimum Q4_K_M quantization level.

  • VioneTM
    link
    fedilink
    English
    arrow-up
    2
    ·
    8 days ago

    Almost all AI Text on Perchance uses the same model. Some are calling other through external API. But based on both that you’ve linked, yes, they are using the same LLM. From what we know from the plugin page ai-text-plugin it is a LLaMa based model, but the specific model is unknown.

  • lemaiOP
    link
    fedilink
    English
    arrow-up
    1
    ·
    8 days ago

    Nobody knows the exact LLaMa model? Its for sure open source and should not be a secret?

    From my actual tests with the same prompt given to different models i would also say its a LLaMa based model. But which exactly? Because it works for my need perfectly.