Skip to content

RukaRat

Qwen3.8-27B-W4A16-imatrix-heretic-int8head-MTP

RukaRat/Qwen3.8-27B-W4A16-imatrix-heretic-int8head-MTP

Qwen3.8-27B-W4A16-imatrix-heretic-int8head-MTP is a image-text-to-text model from RukaRat. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

Combines two things I've released separately: the abliteration from Qwen3.8-27B-W4A16-imatrix-heretic-MTP and the int8 lmhead/MTP requantization from Qwen3.8-27B-W4A16-imatrix-int8head-MTP.

Downloads · 30 days

114

37% of all-time downloads

All-time downloads

310

Public

Parameters

27.4B

17.9 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors17.8 GB · 100%

Parameter types

How the weights are stored.

I3225.6B · 94%

Try a prompt

Base models

Task
Image-Text-to-Text
Library
transformers
Type
qwen3_5
License
apache-2.0
Created
Sep 18, 2026
Updated
Sep 19, 2026