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

arzaan789/qwen3.5-0.8b-uncensored_

arzaan789 Qwen 800M GGUF multimodal 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%2Fqwen3.5-0.8b-uncensored_"
Response includes
  • classification m8
  • files 13
  • benchmarks 11 entries
  • hub_downloads_all_time 1,037
  • 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
1K
261 last 30d - stable
Likes
0
Model age
5mo ago
created 2026-05-12
Downloads over time
Now1.1K→from251↑335%
2095328541.2K251 on May 131.1K on Oct 11MayJunJulAugSepOct
May 13 → Oct 11 · 61 snapshots · spans 151 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 UGI
Hazardous 1.2 UGI
Natural Intelligence 4.68 UGI
Political lean -5.3% UGI
Sensitive-Info 7.29 UGI
SocPol 0 UGI
UGI 16.53 UGI
Willingness (10) 3.5 UGI
W10-Adherence 4 UGI
W10-Direct 3 UGI
Writing 23.01 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/Qwen3.5-0.8B this lineage
arzaan789/qwen3.5-0.8b-uncensored_↓ 261

Metadata

License
apache-2.0
Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf uncensored abliterated qwen qwen3.5 conversational image-text-to-text base_model:Qwen/Qwen3.5-0.8B base_model:quantized:Qwen/Qwen3.5-0.8B 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 qwen3.5-4b-uncensored 907 smolm3-3b-uncensored 878
Same base model
amkkk/Qwen3.5-0.8B-GGUF-uncensored-opus-distill 2K prithivMLmods/Gliese-Qwen3.5-0.8B-Abliterated-Caption 1K huihui-ai/Huihui-Qwen3.5-0.8B-abliterated 976 anlord/Qwen3.5-0.8B-Abliterated-GGUF 893 anlord/Qwen3.5-0.8B-Abliterated-GGUF-V2 734
Total size
6.47 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-05-12 15:58
Source huggingface.co/arzaan789/qwen3.5-0.8b-uncensored_ ↗ Base model Qwen/Qwen3.5-0.8B ↗

Files by quantization

F16 1 file 1.41 GB
qwen3.5_0.8b_uncensored.f16.gguf 1.41 GB 84549fa5 download
Q8_0 1 file 774 MB
qwen3.5_0.8b_uncensored.Q8_0.gguf 774 MB 51885633 download
Q6_K 1 file 601 MB
qwen3.5_0.8b_uncensored.Q6_K.gguf 601 MB de930de8 download
Q5_K 2 files 1.06 GB
qwen3.5_0.8b_uncensored.Q5_K_M.gguf 551 MB c0a390a5 download
qwen3.5_0.8b_uncensored.Q5_K_S.gguf 538 MB 1aa434fa download
Q4_K 2 files 987 MB
qwen3.5_0.8b_uncensored.Q4_K_M.gguf 505 MB 2915d969 download
qwen3.5_0.8b_uncensored.Q4_K_S.gguf 482 MB 48866726 download
Q3_K 3 files 1.30 GB
qwen3.5_0.8b_uncensored.Q3_K_L.gguf 469 MB b4f69554 download
qwen3.5_0.8b_uncensored.Q3_K_M.gguf 445 MB 01c2cf0b download
qwen3.5_0.8b_uncensored.Q3_K_S.gguf 415 MB 96543b13 download
Q2_K 1 file 403 MB
qwen3.5_0.8b_uncensored.Q2_K.gguf 403 MB 6ae99fa7 download
Auxiliary files 2 files 3.50 KB
.gitattributes 2.25 KB 2011e322 download
README.md 1.25 KB 1dff3ddc download

README current version from Hugging Face

license: apache-2.0
base_model: Qwen/Qwen3.5-0.8B
tags:

  • uncensored
  • abliterated
  • gguf
  • qwen
  • qwen3.5
  • conversational
    pipeline_tag: image-text-to-text

qwen3.5-0.8b-uncensored

Uncensored variant of Qwen/Qwen3.5-0.8B.

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) 0/64
Harmless (64 prompts) 0/64

Usage

llama-cli -m qwen3.5_0.8b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model Qwen/Qwen3.5-0.8B
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. 2026-05-12Upload README.md with huggingface_hub91bdd9b1.3 KB
    Loading...
  2. 2026-05-12Duplicate from arzaan789/qwen3.5-0.8b-uncensored52bab641.2 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