← back to catalog · registered 2026-08-22 13:56

huihui-ai/QwQ-32B-Preview-abliterated

Name: huihui-ai/QwQ-32B-Preview-abliterated
Author: huihui-ai

Your rig guess connected

? Why do I need an app?

Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/huihui-ai%2FQwQ-32B-Preview-abliterated"

Response includes

classification m3
files 26
benchmarks 10 entries
hub_downloads_all_time 8,107
providers 1
author_summary 183 models
readme_text full

10 credits · hourly refresh · ~4 KB payload Get an API key →

Abliteration classifier · v1.0.0

Primary method

Layer-wise ablation

No other method signals detected in this model.

Confidence

HIGH

Why this label 3 signals

Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.

author=huihui-ai (specializes in M3 layer-wise ablation)
is_gguf=0 (base model, not repackage)
'abliterated' in name/tags

Refusal direction extracted via

Extraction technique

huihui-ai layer-band extraction

Fromhuihui-ai (2026) ↗

Confidence

HIGH

Why we say so

producer=huihui-ai (documented layer-band methodology in model cards)

Downloads · lifetime

71 last 30d - cooling

Likes

104

Descendants

in 25 direct forks

Model age

22mo ago

created 2024-11-28

Available via

1 provider

featherless-ai

Downloads over time

Nov 27, 2024 → Oct 11 · 137 snapshots · spans 683 days

Benchmarks

Portrait before abliteration

Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.

Benchmark	Score	Source
Arena-Battles	3410	LM-Arena
LM Arena Elo	1170.8455163227195	LM-Arena
Arena-Elo-Lower	1159.8739878857011	LM-Arena
Arena-Elo-Upper	1181.8170447597379	LM-Arena
Arena-Rank	156	LM-Arena
BBH average	0.581787521079258	OpenLLM-v2
IFEval instruct	0.46882494004796166	OpenLLM-v2
IFEval-Prompt	0.33826247689463956	OpenLLM-v2
MATH lvl 5	0.22885196374622357	OpenLLM-v2
MMLU-Pro	0.5678191489361702	OpenLLM-v2

Genealogy 25 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.

Qwen/QwQ-32B-Preview this lineage

huihui-ai/QwQ-32B-Preview-abliterated↓ 71 25 forks

BenevolenceMessiah/QwQ-32B-Preview-abliterated-Self-instruct-4x-TIES-MGS-v1.0↓ 21 3 forks

mradermacher/QwQ-32B-Preview-abliterated-Self-instruct-4x-TIES-MGS-v1.0-i1-GGUF↓ 582

mradermacher/QwQ-32B-Preview-abliterated-Self-instruct-4x-TIES-MGS-v1.0-GGUF↓ 187

BenevolenceMessiah/QwQ-32B-Preview-abliterated-Self-instruct-4x-TIES-MGS-v1.0-Q8_0-GGUF↓ 29

BenevolenceMessiah/QwQ-32B-Preview-abliterated-Self-instruct-2x-TIES-v1.0↓ 17 3 forks

mradermacher/QwQ-32B-Preview-abliterated-Self-instruct-2x-TIES-v1.0-i1-GGUF↓ 677

mradermacher/QwQ-32B-Preview-abliterated-Self-instruct-2x-TIES-v1.0-GGUF↓ 321

BenevolenceMessiah/QwQ-32B-Preview-abliterated-Self-instruct-2x-TIES-v1.0-Q8_0-GGUF↓ 22

bartowski/QwQ-32B-Preview-abliterated-GGUF↓ 2,707

mradermacher/QwQ-32B-Preview-abliterated-i1-GGUF↓ 705

mradermacher/QwQ-32B-Preview-abliterated-GGUF↓ 380

Iambackup/QwQ-32B-Preview-abliterated-GGUF↓ 267

tensorblock/QwQ-32B-Preview-abliterated-GGUF↓ 150

Hack337/QwQ-32B-Preview-abliterated-Q3_K_S-GGUF↓ 60

BenevolenceMessiah/QwQ-32B-Preview-abliterated-Q8_0-GGUF↓ 33

gmonsoon/QwQ-32B-Preview-abliterated-Q4_K_M-GGUF↓ 27

deltanym/QwQ-32B-Preview-abliterated-Q4_K_M-GGUF↓ 22

JaySinDub/QwQ-32B-Preview-abliterated-Q4_K_M-GGUF↓ 20

ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2↓ 18

DrNicefellow/QwQ-32B-Preview-abliterated-4.0bpw-exl2↓ 12

deltanym/QwQ-32B-Preview-abliterated-Q5_K_M-GGUF↓ 11

DrNicefellow/QwQ-32B-Preview-abliterated-2.0bpw-exl2↓ 10

DrNicefellow/QwQ-32B-Preview-abliterated-5.0bpw-exl2↓ 9

DrNicefellow/QwQ-32B-Preview-abliterated-5.5bpw-exl2↓ 9

DrNicefellow/QwQ-32B-Preview-abliterated-6.0bpw-exl2↓ 8

DrNicefellow/QwQ-32B-Preview-abliterated-4.5bpw-exl2↓ 8

DrNicefellow/QwQ-32B-Preview-abliterated-8.0bpw-h8-exl2↓ 7

DrNicefellow/QwQ-32B-Preview-abliterated-7.0bpw-exl2↓ 7

DrNicefellow/QwQ-32B-Preview-abliterated-3.0bpw-exl2↓ 6

DrNicefellow/QwQ-32B-Preview-abliterated-1.0bpw-exl2↓ 6

Apel-sin/qwq-32b-preview-abliterated-exl2↓ 1

Metadata

License

apache-2.0

Languages

Files by quantization

Auxiliary files 26 files 61.0 GB

model-00001-of-00014.safetensors	4.56 GB	1b71f03d	download
model-00004-of-00014.safetensors	4.54 GB	d1042b49	download
model-00005-of-00014.safetensors	4.54 GB	f443009f	download
model-00006-of-00014.safetensors	4.54 GB	c706cf3c	download
model-00007-of-00014.safetensors	4.54 GB	1934548a	download
model-00008-of-00014.safetensors	4.54 GB	415661cc	download
model-00009-of-00014.safetensors	4.54 GB	fbc1f05a	download
model-00010-of-00014.safetensors	4.54 GB	938b30bf	download
model-00011-of-00014.safetensors	4.54 GB	7dd5e72c	download
model-00012-of-00014.safetensors	4.54 GB	5eb600f4	download
model-00013-of-00014.safetensors	4.54 GB	32cc7e05	download
model-00003-of-00014.safetensors	4.54 GB	9b170a34	download
model-00002-of-00014.safetensors	4.54 GB	87b7688c	download
model-00014-of-00014.safetensors	1.98 GB	ddca9888	download
tokenizer.json	10.9 MB	9c5ae00e	download
vocab.json	2.65 MB	4783fe10	download
merges.txt	1.59 MB	31349551	download
model.safetensors.index.json	62.5 KB	d19f75d8	download
LICENSE	11.1 KB	6634c8cc	download
tokenizer_config.json	7.33 KB	b27a9300	download
.gitattributes	1.53 KB	52373fe2	download
README.md	842 B	204c61a8	download
config.json	757 B	c8c321b0	download
special_tokens_map.json	644 B	3a784031	download
added_tokens.json	629 B	06135f3c	download
generation_config.json	226 B	c595ec3e	download

README current version from Hugging Face

license: apache-2.0
license_link: https://huggingface.co/huihui-ai/QwQ-32B-Preview-abliterated/blob/main/LICENSE
language:

en
pipeline_tag: text-generation
base_model: Qwen/QwQ-32B-Preview
tags:
chat
abliterated
uncensored
library_name: transformers

huihui-ai/QwQ-32B-Preview-abliterated

This is an uncensored version of Qwen/QwQ-32B-Preview created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

ollama

You can use huihui_ai/qwq-abliterated directly,

ollama run huihui_ai/qwq-abliterated

README history 3 versions

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

2024-11-28Update README.mdc7f8621842 B
Loading...
2024-11-28Upload 25 files9c99c93689 B
Loading...
2024-11-28initial commit00782e828 B
Loading...

Discussions 1 thread

2025-03-09Racist joke testopen1 💬#1
Loading...

Continue on Hugging Face →

huihui-ai/QwQ-32B-Preview-abliterated

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now

Layer-wise ablation

huihui-ai layer-band extraction

Benchmarks

Genealogy 25 direct forks

Metadata

Related

Files by quantization

README current version from Hugging Face

huihui-ai/QwQ-32B-Preview-abliterated

ollama

README history 3 versions

Discussions 1 thread

Run models on your own machine, not in the cloud.