← back to catalog · registered 2026-09-11 18:55

NINI26454/Huihui-Qwen3.6-27B-abliterated-MTP-Q3_K-GGUF

Name: NINI26454/Huihui-Qwen3.6-27B-abliterated-MTP-Q3_K-GGUF
Author: NINI26454

Abliteration classifier · v1.0.0

Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.

Confidence

MEDIUM

Inherited from base model

M1 Direct removal →

Why this label 3 signals

Method inferred from partial signals — repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.

'abliterated' in name/tags
is_gguf=1
assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown

Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

Downloads · 30-day

Likes

Model age

today

created 2026-09-11

Downloads over time

Sep 11 → Sep 12 · 2 snapshots · spans 1 day

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

huihui-ai/Huihui-Qwen3.6-27B-abliterated↓ 4,524 this lineage

NINI26454/Huihui-Qwen3.6-27B-abliterated-MTP-Q3_K-GGUF↓ 69

Metadata

License

apache-2.0

Quantizations

Q3_K

Files by quantization

Q3_K 1 file 12.6 GB

Huihui-Qwen3.6-27B-abliterated-ggml-model-Q3_K.gguf

12.6 GB

dc128116

download

F16 1 file 885 MB

mmproj-model-f16.gguf

885 MB

dca6010f

download

Auxiliary files 3 files 2.96 KB

.gitattributes	1.63 KB	d15919d3	download
README.md	1.01 KB	8addd953	download
Modelfile	330 B	4a8b3b89	download

README current version from Hugging Face

license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3.6-27B-abliterated
tags:

gguf
ollama
qwen
abliterated
3bit
mtp

Huihui-Qwen3.6-27B-abliterated-MTP-Q3_K-GGUF

3-bit GGUF quantization of huihui-ai/Huihui-Qwen3.6-27B-abliterated.

Files Included

Huihui-Qwen3.6-27B-abliterated-ggml-model-Q3_K.gguf (3-bit quantization, 13.5 GB)
mmproj-model-f16.gguf (Multimodal vision projector, 927 MB)
Modelfile (Ready-to-use Ollama Modelfile)

How to Run with Ollama

Place both the .gguf file and Modelfile in the same directory.
Run:

ollama create qwen3.6-27b-abliterated -f Modelfile
ollama run qwen3.6-27b-abliterated

How to Run with llama.cpp

llama-cli -m Huihui-Qwen3.6-27B-abliterated-ggml-model-Q3_K.gguf --mmproj mmproj-model-f16.gguf -p "Hello!"

EOF
rm -rf /teamspace/studios/this_studio/models/export_qwen36_q3/.cache
ls -lh /teamspace/studios/this_studio/models/export_qwen36_q3/

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

2026-09-11Upload folder using huggingface_hubc4aa80a1 KB
Loading...