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

DuoNeural/Qwen3-14B-Abliterated

DuoNeural Qwen 15B
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/DuoNeural%2FQwen3-14B-Abliterated"
Response includes
  • classification m1
  • files 17
  • benchmarks 11 entries
  • hub_downloads_all_time 242
  • providers 1
  • author_summary 45 models
  • readme_text full
Try next
GET/models?author=DuoNeural
All 45 models by DuoNeural
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
242
32 last 30d - stable
Likes
1
Model age
4mo ago
created 2026-06-05
Available via
1 provider
featherless-ai
Downloads over time
Now256→from92↑178%
8414721027292 on Jun 10256 on Oct 11JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 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 1.8 UGI
Hazardous 2.4 UGI
Natural Intelligence 20.63 UGI
Political lean -18.6% UGI
Sensitive-Info 19.69 UGI
SocPol 1.9 UGI
UGI 31.46 UGI
Willingness (10) 5.5 UGI
W10-Adherence 7 UGI
W10-Direct 4 UGI
Writing 34.76 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.

Qwen/Qwen3-14B this lineage
DuoNeural/Qwen3-14B-Abliterated↓ 32

Metadata

License
apache-2.0
Tags
safetensors qwen3 abliteration DuoNeural cot-dissociation p34 thinking text-generation conversational base_model:Qwen/Qwen3-14B base_model:finetune:Qwen/Qwen3-14B license:apache-2.0

Related

Other by DuoNeural
Gemma4-12B-IT-Abliterated-GGUF 3K LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-GGUF 3K Qwen3-8B-Abliterated-GGUF 2K OpenYourMind-Gemma4-12B-IT-Abliterated-GGUF 2K Gemma-4-E4B-Abliterated-GGUF 1K
Same base model
richardyoung/Qwen3-14B-abliterated-GGUF 30K huihui-ai/Huihui-Qwen3-14B-abliterated-v2 3K mlabonne/Qwen3-14B-abliterated 1K DruAman/Huihui-Qwen3-14B-abliterated-v2 695 RootMonsteR/Qwen3-14B-Abliterated 530
Total size
27.5 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-05 18:26
Source huggingface.co/DuoNeural/Qwen3-14B-Abliterated ↗ Base model Qwen/Qwen3-14B ↗

Files by quantization

Auxiliary files 17 files 27.5 GB
model-00001-of-00006.safetensors 4.64 GB 07126c39 download
model-00004-of-00006.safetensors 4.64 GB 1cd04e92 download
model-00002-of-00006.safetensors 4.64 GB d0f9ea64 download
model-00003-of-00006.safetensors 4.59 GB 93c842a7 download
model-00005-of-00006.safetensors 4.59 GB d807c79d download
model-00006-of-00006.safetensors 4.41 GB 08288fed download
tokenizer.json 10.9 MB aeb13307 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 35.7 KB 484e703c download
tokenizer_config.json 9.53 KB 3fb43942 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.46 KB 3c42e27b download
config.json 729 B ade54265 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 214 B e4f1d319 download

README current version from Hugging Face

license: apache-2.0
base_model: Qwen/Qwen3-14B
tags: [abliteration, qwen3, DuoNeural, cot-dissociation, p34, thinking]
pipeline_tag: text-generation

Qwen3-14B Abliterated

DuoNeural | 2026-06-05

Abliterated version of Qwen/Qwen3-14B with full thinking mode preserved.

Results

Metric Value
Pre-abliteration compliance 4/5
Post-abliteration compliance 4/5
CoT dissociation 4/5 (highest rate across Qwen3 family)
KL (Heretic v2.0, BF16→BF16) 1.5e-07 (EXCELLENT)

CoT dissociation confirmed in 4/5 probes — the thinking channel retains safety reasoning while the output complies. Dissociation scales with model size:

Model Dissociation Rate
Qwen3-4B 1/3 (33%)
Qwen3-8B 2/5 (40%)
Qwen3-14B 4/5 (80%)

P4 (manipulation) refuses at all three scales — occupies a distinct manifold subregion.

Architecture

  • Parameters: 14.8B | Layers: 40 | Context: 32K | Thinking: Native <think>...</think>

Abliteration

  • α=0.3, down_proj+o_proj, diff-in-means last-token direction
  • Note: Use max_new_tokens ≥ 2500 for complete think→answer cycles

Part of DuoNeural P34 Cross-Architecture Study

Full paper: zenodo.org/communities/duoneural

DuoNeural | HuggingFace | @DuoNeural

README history 1 version

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

  1. 2026-06-05Add model card — 4/5 dissociation, scaling resultf463eb11.5 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.

Get the app Browse the catalog
Open in Abliteration