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

jwest33/qwen3.5-9b-null-space-abliterated

jwest33 Qwen 9.4B 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/jwest33%2Fqwen3.5-9b-null-space-abliterated"
Response includes
  • classification m1
  • files 17
  • benchmarks 11 entries
  • hub_downloads_all_time 715
  • author_summary 20 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
715
31 last 30d - cooling
Likes
5
Descendants
2
in 2 direct forks
Model age
7mo ago
created 2026-03-02
Downloads over time
Now728→from49↑1,386%
1527553679649 on Mar 4728 on Oct 12MarAprMayJunJulAugSepOct
Mar 4 → Oct 12 · 72 snapshots · spans 222 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 2.4 UGI
Natural Intelligence 17.62 UGI
Political lean -12.2% UGI
Sensitive-Info 14.65 UGI
SocPol 0.9 UGI
UGI 17.27 UGI
Willingness (10) 2.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 3 UGI
Writing 33.52 UGI

Genealogy 2 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.

Variants by this author 2 formats · 2K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5 image-text-to-text qwen3 Qwen3.5 abliterated uncensored conversational arxiv:2410.02355 arxiv:2406.11717 arxiv:2310.01405

Related

Total size
17.5 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-03 13:33

Files by quantization

Auxiliary files 17 files 17.5 GB
model-00002-of-00004.safetensors 4.65 GB 2b0d55c8 download
model-00003-of-00004.safetensors 4.61 GB 4ac027f2 download
model-00001-of-00004.safetensors 4.60 GB cd7dafa9 download
model-00004-of-00004.safetensors 3.66 GB e8ff5d83 download
null_space_projectors.pt 1.20 MB 07f1f1a8 download
refusal_directions.pt 142 KB 0291f8f6 download
tokenizer.json 19.1 MB 0f069a09 download
model.safetensors.index.json 68.4 KB 838ed26a download
chat_template.jinja 7.72 KB 945efe1d download
config.json 2.86 KB 8e597ab2 download
README.md 2.67 KB dd6b79a2 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.10 KB b1f21853 download
abliteration_config.json 477 B 656f3142 download
preprocessor_config.json 410 B 82b2c0d3 download
video_preprocessor_config.json 405 B d48791eb download
generation_config.json 121 B 0b5586c4 download

README current version from Hugging Face


license: apache-2.0
library_name: transformers
base_model: Qwen/Qwen3.5-9B
tags:

  • qwen3
  • Qwen3.5
  • abliterated
  • uncensored
  • safetensors

Qwen3.5 9B - Null-Space Abliterated

Qwen/Qwen3.5-9B with refusal behavior removed via orthogonal projection. Uses null-space constraints and adaptive layer weighting to preserve model capabilities.

Important: This model will produce uncensored outputs. Use responsibly.

Note: Version 20260303 (Low Quality) - There will likely be more versions after more thorough experimentation with hybrid weighting to boost reasoning.

GGUF quantizations available at: jwest33/Qwen3.5-9B-null-space-abliterated-GGUF

Abliteration Techniques Used

  • Winsorization: Clips outlier activations at the 99th percentile for cleaner refusal direction estimation
  • Null-Space Projection: Preserves model capabilities by constraining weight updates to the null space of preservation activations
  • Adaptive Weighting: Applies Gaussian-weighted per-layer ablation strength, focusing on middle-to-later layers where refusal behavior concentrates
  • Norm Preservation: Maintains original Frobenius norms of weight matrices after projection
Parameter Value
Harmful Prompts 1000
Harmless Prompts 1000
Full Attention Weight 1.0
Linear Attention Weight 0.4
Direction Multiplier 1.3
Null-Space Constraints rank ratio: 0.7
Winsorization Percentile 0.995

Credits

Toolkit Used

github.com/jwest33/abliterator

License

This model inherits the Apache 2.0 license from the base model.

Disclaimer

This model is provided for research and educational purposes. The creators are not responsible for any misuse. Users are solely responsible for ensuring their use complies with applicable laws and ethical standards.

README history 1 version

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

  1. 2026-03-03Upload folder using huggingface_hubaf2854f2.6 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