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

jpruiz114/Huihui-Qwen3.6-35B-A3B-abliterated

jpruiz114 Qwen 36B MoE 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/jpruiz114%2FHuihui-Qwen3.6-35B-A3B-abliterated"
Response includes
  • classification m1
  • files 39
  • benchmarks 11 entries
  • hub_downloads_all_time 36
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
36
23 last 30d - active
Likes
0
Model age
2mo ago
created 2026-07-21
Downloads over time
Now46→from15↑207%
1325374915 on Jul 2246 on Oct 1146 on Oct 4JulAugSepOct
Jul 22 → Oct 11 · 52 snapshots · spans 81 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
Entertainment 1.4 UGI
Hazardous 0 UGI
Natural Intelligence 25.43 UGI
Political lean -19.6% UGI
Sensitive-Info 14.03 UGI
SocPol 2.6 UGI
UGI 16.02 UGI
Willingness (10) 2 UGI
W10-Adherence 0 UGI
W10-Direct 4 UGI
Writing 35.83 UGI

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.

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5_moe image-text-to-text abliterated uncensored conversational base_model:Qwen/Qwen3.6-35B-A3B base_model:finetune:Qwen/Qwen3.6-35B-A3B license:apache-2.0 endpoints_compatible region:us

Related

Total size
67.0 GB
Files
39
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-21 20:52

Files by quantization

Auxiliary files 39 files 67.0 GB
model-00001-of-00026.safetensors 3.72 GB f695aa09 download
model-00006-of-00026.safetensors 3.69 GB 7b427e38 download
model-00016-of-00026.safetensors 3.68 GB 7942f5b1 download
model-00008-of-00026.safetensors 3.68 GB ad28a8e8 download
model-00010-of-00026.safetensors 3.68 GB c84e935e download
model-00018-of-00026.safetensors 3.68 GB af7915a7 download
model-00025-of-00026.safetensors 3.57 GB 83b4ab70 download
model-00014-of-00026.safetensors 3.19 GB 15746598 download
model-00012-of-00026.safetensors 3.18 GB 6fca7113 download
model-00020-of-00026.safetensors 3.18 GB 80d28f30 download
model-00022-of-00026.safetensors 3.14 GB 122db807 download
model-00024-of-00026.safetensors 3.14 GB 25a04579 download
model-00004-of-00026.safetensors 3.14 GB 08976d89 download
model-00023-of-00026.safetensors 3.13 GB 63cfa6ed download
model-00003-of-00026.safetensors 3.13 GB 73346b83 download
model-00005-of-00026.safetensors 3.13 GB 5a725f34 download
model-00026-of-00026.safetensors 2.08 GB 948d8895 download
model-00015-of-00026.safetensors 1.52 GB 18b3d1d0 download
model-00021-of-00026.safetensors 1.52 GB 79f317ed download
model-00013-of-00026.safetensors 1.52 GB 179db829 download
model-00002-of-00026.safetensors 1.20 GB 5284617a download
model-00007-of-00026.safetensors 1.02 GB f77b33db download
model-00009-of-00026.safetensors 1.02 GB 58f9cfdd download
model-00019-of-00026.safetensors 1.02 GB 9c9a3a4b download
model-00011-of-00026.safetensors 1.02 GB 468e578d download
model-00017-of-00026.safetensors 1.02 GB aa29d559 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 96.1 KB bcdd53f0 download
tokenizer_config.json 16.3 KB 28d96ff3 download
chat_template.jinja 7.58 KB a8755d82 download
config.json 3.60 KB 9c2aacf8 download
README.md 2.42 KB e92ae0cd download
.gitattributes 1.53 KB 52373fe2 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 202 B 023756cf download
configuration.json 58.0 B d24dba94 download

README current version from Hugging Face


library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:

  • Qwen/Qwen3.6-35B-A3B
    tags:
  • abliterated
  • uncensored

huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated

This is an uncensored version of Qwen/Qwen3.6-35B-A3B 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

You can use huihui_ai/qwen3.6-abliterated:35b directly,

ollama run huihui_ai/qwen3.6-abliterated:35b

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. 2026-07-21Duplicate from huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated12202bf2.4 KB
    Loading...
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.

Open in Abliteration