← back to catalog · registered 2026-11-12 18:03

letuan/Huihui-Qwen3.6-35B-A3B-abliterated-FP8

letuan Qwen 35B 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/letuan%2FHuihui-Qwen3.6-35B-A3B-abliterated-FP8"
Response includes
  • classification m1
  • files 39
  • benchmarks 11 entries
  • author_summary 4 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 · 30-day
45
Likes
0
Model age
1w ago
created 2026-11-12
Downloads over time
Now 45 → from 0 ↑ 0%
0173350 0 on Nov 12 45 on Nov 22 45 on Nov 21 Nov
Nov 12 → Nov 22 · 11 snapshots · spans 10 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:quantized:Qwen/Qwen3.6-35B-A3B license:apache-2.0 endpoints_compatible compressed-tensors

Related

Total size
35.7 GB
Files
39
Quantizations
1
Registered
2026-11-12 18:03
Last updated on HF
2026-11-12 17:09

Files by quantization

Auxiliary files 39 files 35.8 GB
model-00001-of-00026.safetensors 2.41 GB 15dd5232 download
model-00025-of-00026.safetensors 2.29 GB 5bd24c4c download
model-00006-of-00026.safetensors 1.85 GB 277165f2 download
model-00016-of-00026.safetensors 1.84 GB 6853094d download
model-00010-of-00026.safetensors 1.84 GB 978114b8 download
model-00018-of-00026.safetensors 1.84 GB a96bbbea download
model-00008-of-00026.safetensors 1.84 GB 32b9ac98 download
model-00026-of-00026.safetensors 1.80 GB 3b884e47 download
model-00014-of-00026.safetensors 1.60 GB a06ad273 download
model-00020-of-00026.safetensors 1.59 GB ab310eb4 download
model-00012-of-00026.safetensors 1.59 GB 6e51781b download
model-00022-of-00026.safetensors 1.57 GB 9d5587c2 download
model-00024-of-00026.safetensors 1.57 GB 4a8176ee download
model-00004-of-00026.safetensors 1.57 GB ad96b68b download
model-00023-of-00026.safetensors 1.57 GB 22621f97 download
model-00003-of-00026.safetensors 1.57 GB 0a578c99 download
model-00005-of-00026.safetensors 1.57 GB d3070dd9 download
model-00002-of-00026.safetensors 964 MB 3b8d3017 download
model-00015-of-00026.safetensors 783 MB 1c3d049f download
model-00013-of-00026.safetensors 782 MB 8506cfd1 download
model-00021-of-00026.safetensors 782 MB 68e06715 download
model-00011-of-00026.safetensors 527 MB 07808ce1 download
model-00019-of-00026.safetensors 527 MB 56af4d34 download
model-00009-of-00026.safetensors 527 MB e4ca7ccd download
model-00007-of-00026.safetensors 526 MB d49416b6 download
model-00017-of-00026.safetensors 525 MB 6ebb40bf download
tokenizer.json 12.2 MB 5f9e4d49 download
model.safetensors.index.json 6.54 MB e619d93b download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
tokenizer_config.json 16.3 KB 28d96ff3 download
chat_template.jinja 7.58 KB a8755d82 download
config.json 4.24 KB cf0b3482 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. 2026-11-12 Upload folder using huggingface_hub 312d713 2.4 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