unsloth
/

Qwen3-30B-A3B-128K-GGUF

Text Generation

Model card Files Files and versions

UD-Q5_K_XL ?

#3

by AaronFeng753 - opened Apr 30

Apr 30

since Q5KM is 21.7 GB, a UD-Q5_K_XL gguf should be around 20GB~ and can be fully loaded into a 24gb card

Thank you for these UD ggufs!

Unsloth AI org Apr 30

Thanks for the suggestion we'll see what we can do :)

Unsloth AI org 30 days ago

We've uploaded them all now

Also with a new improved calibration dataset :)

CC: @AaronFeng753 @truder @PonderosaSharon

30 days ago

We've uploaded them all now

Also with a new improved calibration dataset :)

CC: @AaronFeng753 @truder @PonderosaSharon

Thank you so much! Have a nice day!

AaronFeng753 changed discussion status to closed 30 days ago

combin8

28 days ago

We've uploaded them all now

Also with a new improved calibration dataset :)

@shimmyshimmer Did you upload the calibration dataset? I am having trouble finding it.

Also, I wonder if you all might collaborate with @awni since he’s experimenting with calibration datasets for Qwen (using MLX’s DWQ).

Unsloth AI org 28 days ago

We've uploaded them all now

Also with a new improved calibration dataset :)

@shimmyshimmer Did you upload the calibration dataset? I am having trouble finding it.

Also, I wonder if you all might collaborate with @awni since he’s experimenting with calibration datasets for Qwen (using MLX’s DWQ).

We meant we uploaded the new Q5 XL etc quants. Could be interesting!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment