basecompute
/

Qwen3.8-27B

Text Generation

Model card Files Files and versions

What profile did these models use?

#1

by bangbangkido - opened 12 days ago

Converted with https://github.com/basecompute/baseRT/blob/main/base-convert/profiles/dense-q4mix.json ?

fabian-basecompute

Base Compute org 10 days ago

Thanks for testing Qwen3.8, the weights are quantized with the default-q4 profile (https://github.com/basecompute/baseRT/blob/main/base-convert/profiles/default-q4.json)

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