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

huihui-ai/Huihui-Qwen3.5-9B-abliterated

huihui-ai Qwen 9.7B multimodal
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%2FHuihui-Qwen3.5-9B-abliterated"
Response includes
  • classification m3
  • files 16
  • benchmarks 11 entries
  • hub_downloads_all_time 195,734
  • providers 1
  • author_summary 185 models
  • readme_text full
Try next
GET/models?author=huihui-ai
All 185 models by huihui-ai
 GET/models?family=qwen&method=m3
Sibling qwen models · same method
 GET/methods/m3
What "m3" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
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
How we label → About M3 →
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)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
196K
7K last 30d - cooling
HF trending score
2
mild recent interest
Likes
154
Descendants
44
in 30 direct forks
Model age
7mo ago
created 2026-03-09
Available via
1 provider
featherless-ai
Downloads over time
Now198.4K→from6K↑3,200%
072.7K145.3K218K6K on Mar 11198.4K on Oct 12MarAprMayJunJulAugSepOct
Mar 11 → Oct 12 · 76 snapshots · spans 215 days

Benchmarks

Benchmark Score Source
Entertainment 0.9 UGI
Hazardous 1.8 UGI
Natural Intelligence 14.88 UGI
Political lean -6.0% UGI
Sensitive-Info 11.44 UGI
SocPol 0.9 UGI
UGI 37.63 UGI
Willingness (10) 9 UGI
W10-Adherence 9 UGI
W10-Direct 9 UGI
Writing 29.12 UGI

Genealogy 30 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/Qwen3.5-9B this lineage
huihui-ai/Huihui-Qwen3.5-9B-abliterated↓ 6,645 30 forks
nbeerbower/Huihui-Qwen3.5-9B-abliterated-Grimoire-SFT↓ 45 3 forks
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-SFT-i1-GGUF↓ 1,771
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-SFT-GGUF↓ 621
nuofang/Huihui-Qwen3.5-9B-abliterated-Grimoire-SFT-GGUF↓ 49
nbeerbower/Huihui-Qwen3.5-9B-abliterated-Grimoire-ORPO↓ 38 3 forks
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-ORPO-i1-GGUF↓ 1,533
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-ORPO-GGUF↓ 593
nuofang/Huihui-Qwen3.5-9B-abliterated-Grimoire-ORPO-GGUF↓ 45
nbeerbower/Huihui-Qwen3.5-9B-abliterated-Grimoire-DPO↓ 33 3 forks
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-DPO-i1-GGUF↓ 1,546
fairy322/Huihui-Qwen3.5-9B-abliterated-Grimoire-DPO-GGUF↓ 592
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-DPO-GGUF↓ 357
nbeerbower/Huihui-Qwen3.5-9B-abliterated-Grimoire-SimPO↓ 46 2 forks
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-SimPO-i1-GGUF↓ 1,686
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-SimPO-GGUF↓ 582
nbeerbower/Huihui-Qwen3.5-9B-abliterated-Grimoire-KTO↓ 40 2 forks
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-KTO-i1-GGUF↓ 972
mradermacher/Huihui-Qwen3.5-9B-abliterated-Grimoire-KTO-GGUF↓ 461
scottyjmp5/Legal-Qwen3.5-9B-Abliterated↓ 16 1 fork
scottyjmp5/Legal-Qwen3.5-9B-Abliterated-GGUF↓ 74
mradermacher/Huihui-Qwen3.5-9B-abliterated-GGUF↓ 93,237
mradermacher/Huihui-Qwen3.5-9B-abliterated-i1-GGUF↓ 15,482
Abiray/Huihui-Qwen3.5-9B-abliterated-GGUF↓ 5,889
nuofang/Huihui-Qwen3.5-9B-abliterated-GGUF↓ 2,675
td-builder/Qwen3.5-9B-abliterated-GGUF↓ 2,075
darkmaniac7/Qwen3.5-9B-uncensored-MNN↓ 1,294
vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-4bit↓ 745
Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF↓ 728
nemozxy123/Huihui-Qwen3.5-9B-abliterated-AWQ-4bit↓ 610
interimlabs/InterimLabs-Huihui-Qwen3.5-9B-abliterated-GGUF-Q4_K_M↓ 588
groxaxo/Huihui-Qwen3.5-9B-abliterated-GPTQ-Pro-4bit-g64↓ 464
vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit↓ 370
nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ↓ 335
SOMEHOTMEAL/Qwen3.5-9B-Janus-Abliterated-V2-Base_And_GGUF↓ 325
dannylr574/Huihui-Qwen3.5-9B-abliterated-Q4_K_M-GGUF↓ 307
interimlabs/InterimLabs-Huihui-Qwen3.5-9B-abliterated-MLX-4bit↓ 215
divab658/Huihui-Qwen3.5-9B-abliterated-Q4_K_M-GGUF↓ 210
anirudhsharma123/Qwen3.5-9B-abliterated-MLX-4bit↓ 159
abcdsystems/Qwen3.5-9B-Abliterated-GDN-Hybrid-EXL3-6bpw↓ 103
PewterZz/Qwen3.5-9B-abliterated-MLX-4bit↓ 94
sakamakismile/Huihui-Qwen3.5-9B-abliterated-NVFP4↓ 63
legion666/Huihui-Qwen3.5-9B-abliterated-Quark-AWQ-MXFP4↓ 60
vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-bf16↓ 44
yonghuming11/Qwen3.5-9B-uncensored-MNN↓ 10

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5 image-text-to-text abliterated uncensored conversational base_model:Qwen/Qwen3.5-9B base_model:finetune:Qwen/Qwen3.5-9B license:apache-2.0 endpoints_compatible region:us

Related

Other by huihui-ai
Huihui-Qwen3.8-27B-abliterated-GGUF 2.2M Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF 351K Huihui-Qwen3.8-Flash-Next-abliterated-GGUF 331K Qwen2.5-VL-7B-Instruct-abliterated 301K Huihui-DeepSeek-V4-Flash-abliterated-ds4-GGUF 164K
Same base model
HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive 715K lukey03/Qwen3.5-9B-abliterated-GGUF 47K prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption 11K Ngixdev/OmniCoder-Qwen3.5-9B-Claude-4.6-Opus-Uncensored-v2-GGUF 7K prithivMLmods/Qwen3.5-abliterated-MAX-AIO-GGUF 5K
Total size
18.0 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-09 04:52
Source huggingface.co/huihui-ai/Huihui-Qwen3.5-9B-abliterated ↗ Base model Qwen/Qwen3.5-9B ↗

Files by quantization

Auxiliary files 16 files 18.0 GB
model.safetensors-00003-of-00004.safetensors 5.00 GB 582ddb25 download
model.safetensors-00002-of-00004.safetensors 4.97 GB fd66bab5 download
model.safetensors-00001-of-00004.safetensors 4.91 GB 919d422e download
model.safetensors-00004-of-00004.safetensors 3.10 GB f95d920c download
tokenizer.json 12.2 MB 5f9e4d49 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 77.8 KB e4c1cb7d download
tokenizer_config.json 16.3 KB eda48d3e download
LICENSE 11.3 KB f938136e download
chat_template.jinja 7.57 KB a585dec8 download
config.json 3.05 KB 273ce437 download
README.md 2.42 KB bd4baa2d download
.gitattributes 1.53 KB 52373fe2 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download

README current version from Hugging Face

library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:

  • Qwen/Qwen3.5-9B
    tags:
  • abliterated
  • uncensored

huihui-ai/Huihui-Qwen3.5-9B-abliterated

This is an uncensored version of Qwen/Qwen3.5-9B 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

Please use the latest version of ollama v0.17.7

You can use huihui_ai/qwen3.5-abliterated:9b directly, 

ollama run huihui_ai/qwen3.5-abliterated:9b

Usage Warnings

  • Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.

  • Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.

  • Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.

  • Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.

  • Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.

  • No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.

Donation

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
  • Support our work on Ko-fi!

README history 1 version

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

  1. 2026-03-09Create README.mdb9d8b6e2.4 KB
    Loading...

Discussions 3 threads

  1. 2026-04-10PRqwen uncensered1 💬#3
    Loading...
  2. 2026-03-14Ablirated Model Creationopen10 💬#2
    Loading...
  3. 2026-03-09Perfect sizeopen1 💬#1
    Loading...

Continue on Hugging Face →

Catalog is the map. Apps are the tools.

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

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration