Modelpublic

AvatarAndrey/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF

sourceHugging Faceapache-2.0updated 24d agoView on Hugging Face

0likes253downloads

Model Card

Qwen3.8-27B Heretic Abliterated (GGUF) - personal mirror

A pinned personal copy of two files needed to run this model with vision. Nothing was re-quantized or modified: both files are byte-identical to their sources (verified by LFS sha256).

file	size	copied from	source revision
`RVN-Q3_K_S-multilingual-mtp.gguf`	11.7 GiB	0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF	`20b94f0613b632b4848bbe3b1e05d9ee0c2b1608`
`mmproj-Qwen3.8-27B-Q8_0.gguf`	600 MiB	ggml-org/Qwen3.8-27B-GGUF	`0669b98607d47046c7c2b3f801011d54a08cfccf`

The weights are the abliterated build; the multimodal projector (mmproj) comes from the official ggml-org repo. Both are required together - the projector alone does nothing, and the weights alone give you a text-only model.

Usage

bash

llama-server -m RVN-Q3_K_S-multilingual-mtp.gguf              --mmproj mmproj-Qwen3.8-27B-Q8_0.gguf

Mirrored 2026-09-04. Licensed Apache-2.0, same as both sources.