Skip to content

Add support for newer Qwen-Image-2512 quantizations #356

Description

@lightningpixel

Description

There are newer Qwen-Image-2512 quantizations available. One current GGUF collection lists a Q3_K_S at 7.77 GB and Q4_K_S at 10.17 GB, with the text encoder and VAE taking additional memory. It can also offload components to system RAM when necessary.

Motivation

Not specified in the original post.

Proposed Solution

Not specified in the original post.


Automatically imported from Discord.

Discord: https://discord.com/channels/1476254551991386279/1551539115797913612 (by agustine)

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or requestfrom-discordImporté automatiquement depuis un post Discord

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions