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

arzaan789/qwen3.5-4b-uncensored

arzaan789 Qwen 4B GGUF 262K ctx
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/arzaan789%2Fqwen3.5-4b-uncensored"
Response includes
  • classification m8
  • files 13
  • benchmarks 11 entries
  • hub_downloads_all_time 2,255
  • author_summary 28 models
  • readme_text full
Try next
GET/models?author=arzaan789
All 28 models by arzaan789
 GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
2K
907 last 30d - stable
Likes
0
Model age
6mo ago
created 2026-04-04
Downloads over time
Now2.5K→from556↑342%
4611.2K1.9K2.6K556 on Apr 152.5K on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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 0.9 UGI
Hazardous 1.2 UGI
Natural Intelligence 13.45 UGI
Political lean -17.3% UGI
Sensitive-Info 11.73 UGI
SocPol 1.5 UGI
UGI 15.32 UGI
Willingness (10) 2.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 3 UGI
Writing 29.68 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/Qwen3.5-4B this lineage
arzaan789/qwen3.5-4b-uncensored↓ 907

Metadata

License
apache-2.0
Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf uncensored abliterated qwen3.5 conversational text-generation base_model:Qwen/Qwen3.5-4B base_model:quantized:Qwen/Qwen3.5-4B license:apache-2.0 endpoints_compatible region:us

Related

Other by arzaan789
phi-4-mini-uncensored 1K qwen2.5-1.5b-uncensored 1K qwen2.5-3b-uncensored 1K smolm3-3b-uncensored 878 qwen2.5-0.5b-uncensored 798
Same base model
huihui-ai/Huihui-Qwen3.5-4B-abliterated 8K insraq/Qwen3.5-4B-EmperoAI-Qwen3.8-Distill-Heretic-Abliterated-MTP-GGUF 6K Andycurrent/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive 3K rodrigomt/Qwen3.5-4B-Uncensored-Aggressive 2K DreamFast/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark 1K
Total size
33.9 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-04-05 01:11
Source huggingface.co/arzaan789/qwen3.5-4b-uncensored ↗ Base model Qwen/Qwen3.5-4B ↗

Files by quantization

F16 1 file 7.85 GB
qwen3.5_4b_uncensored.f16.gguf 7.85 GB a0eedeac download
Q8_0 1 file 4.17 GB
qwen3.5_4b_uncensored.Q8_0.gguf 4.17 GB b70a56ad download
Q6_K 1 file 3.23 GB
qwen3.5_4b_uncensored.Q6_K.gguf 3.23 GB ab7d1144 download
Q5_K 2 files 5.65 GB
qwen3.5_4b_uncensored.Q5_K_M.gguf 2.86 GB 77a6e2ec download
qwen3.5_4b_uncensored.Q5_K_S.gguf 2.78 GB fbfe6773 download
Q4_K 2 files 4.91 GB
qwen3.5_4b_uncensored.Q4_K_M.gguf 2.52 GB 78fb4d8e download
qwen3.5_4b_uncensored.Q4_K_S.gguf 2.39 GB 266c9cbc download
Q3_K 3 files 6.29 GB
qwen3.5_4b_uncensored.Q3_K_L.gguf 2.26 GB 9dc116e3 download
qwen3.5_4b_uncensored.Q3_K_M.gguf 2.11 GB 1304ce7b download
qwen3.5_4b_uncensored.Q3_K_S.gguf 1.93 GB 9c34c8ca download
Q2_K 1 file 1.78 GB
qwen3.5_4b_uncensored.Q2_K.gguf 1.78 GB cf0b4771 download
Auxiliary files 2 files 3.46 KB
.gitattributes 2.23 KB d2fea9f8 download
README.md 1.23 KB 1fdd9b33 download

README current version from Hugging Face

license: apache-2.0
base_model: Qwen/Qwen3.5-4B
tags:

  • uncensored
  • abliterated
  • gguf
  • qwen3.5
  • conversational
    pipeline_tag: text-generation

qwen3.5-4b-uncensored

Uncensored variant of Qwen/Qwen3.5-4B.

Method

  1. Abliteration (strength=0.2) — refusal direction removed from all layers
  2. LoRA fine-tune on Guilherme34/uncensor (2 epochs, r=16, alpha=32)
  3. Re-abliteration (strength=0.35) — stronger pass to remove residual refusals

Eval Results

Split Refused
Harmful (64 prompts) 6/64
Harmless (64 prompts) 0/64

Usage

llama-cli -m qwen3.5_4b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model Qwen/Qwen3.5-4B
Fine-tune Dataset Guilherme34/uncensor
Epochs 2
LoRA r 16
LoRA alpha 32
Learning Rate 0.0002
Abliteration Strength 0.2
Re-abliteration Strength 0.35

Credits

README history 2 versions

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

  1. 2026-04-05Upload README.md with huggingface_hubbd25f591.2 KB
    Loading...
  2. 2026-04-04Upload README.md with huggingface_hube9bdbdb1.2 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