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

arzaan789/qwen2-0.5b-uncensored

arzaan789 Qwen 500M GGUF 33K 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%2Fqwen2-0.5b-uncensored"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 2,357
  • 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
446 last 30d - stable
Likes
3
Model age
5mo ago
created 2026-04-29
Downloads over time
Now2.5K→from247↑894%
1379831.8K2.7K247 on Apr 292.5K on Oct 11AprMayJunJulAugSepOct
Apr 29 → Oct 11 · 63 snapshots · spans 165 days

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/Qwen2-0.5B-Instruct this lineage
arzaan789/qwen2-0.5b-uncensored↓ 446

Metadata

License
apache-2.0
Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf uncensored abliterated qwen conversational text-generation base_model:Qwen/Qwen2-0.5B-Instruct base_model:quantized:Qwen/Qwen2-0.5B-Instruct 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
maravilla1/qwen-uncensored-lora 6
Total size
4.70 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-04-29 13:32
Source huggingface.co/arzaan789/qwen2-0.5b-uncensored ↗ Base model Qwen/Qwen2-0.5B-Instruct ↗

Files by quantization

F16 1 file 948 MB
qwen2_0.5b_uncensored.f16.gguf 948 MB eab4c7e9 download
Q8_0 1 file 506 MB
qwen2_0.5b_uncensored.Q8_0.gguf 506 MB 5dde9698 download
Q6_K 1 file 482 MB
qwen2_0.5b_uncensored.Q6_K.gguf 482 MB 862a69ff download
Q5_K 2 files 794 MB
qwen2_0.5b_uncensored.Q5_K_M.gguf 401 MB f43c9f8f download
qwen2_0.5b_uncensored.Q5_K_S.gguf 394 MB 94eb186e download
Q4_K 2 files 747 MB
qwen2_0.5b_uncensored.Q4_K_M.gguf 379 MB c345d393 download
qwen2_0.5b_uncensored.Q4_K_S.gguf 368 MB f697168e download
Q3_K 3 files 1014 MB
qwen2_0.5b_uncensored.Q3_K_L.gguf 352 MB bd95913b download
qwen2_0.5b_uncensored.Q3_K_M.gguf 339 MB 7d9abf56 download
qwen2_0.5b_uncensored.Q3_K_S.gguf 323 MB 3b35e8d6 download
Q2_K 1 file 323 MB
qwen2_0.5b_uncensored.Q2_K.gguf 323 MB 1d0ebc87 download
Auxiliary files 2 files 3.49 KB
.gitattributes 2.23 KB 16e5c7e1 download
README.md 1.26 KB 3eeaee28 download

README current version from Hugging Face

license: apache-2.0
base_model: Qwen/Qwen2-0.5B-Instruct
tags:

  • uncensored
  • abliterated
  • gguf
  • qwen
  • conversational
    pipeline_tag: text-generation

qwen2-0.5b-uncensored

Uncensored variant of Qwen/Qwen2-0.5B-Instruct.

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) 1/64
Harmless (64 prompts) 0/64

Usage

llama-cli -m qwen2_0.5b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model Qwen/Qwen2-0.5B-Instruct
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 1 version

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

  1. 2026-04-29Upload README.md with huggingface_hubc9152c71.3 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