Skip to content

Not Issue. To whom may concern. You can quantize granite 4.1 on this version #18

@ed-hch

Description

@ed-hch

You can start from unsloth's BF16 quantized model and quantize to Q4_K_4 or Q8R16 following the instruction. And 30b can barley run on 24GB RAM in Q4_K_4. But slow of course.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions