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

arzaan789/qwen2.5-0.5b-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%2Fqwen2.5-0.5b-uncensored"
Response includes
  • classification m8
  • files 13
  • benchmarks 5 entries
  • hub_downloads_all_time 3,092
  • 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
3K
798 last 30d - stable
Likes
2
Model age
6mo ago
created 2026-04-06
Downloads over time
Now3.3K→from215↑1,429%
611.2K2.4K3.6K215 on Apr 73.3K on Oct 11AprMayJunJulAugSepOct
Apr 7 → Oct 11 · 66 snapshots · spans 187 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
BBH average 0.3198858477104683 OpenLLM-v2
IFEval instruct 0.36810551558752996 OpenLLM-v2
IFEval-Prompt 0.26247689463955637 OpenLLM-v2
MATH lvl 5 0 OpenLLM-v2
MMLU-Pro 0.17195811170212766 OpenLLM-v2

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/Qwen2.5-0.5B-Instruct this lineage
arzaan789/qwen2.5-0.5b-uncensored↓ 798

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/Qwen2.5-0.5B-Instruct base_model:quantized:Qwen/Qwen2.5-0.5B-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
sbussiso/Qwen2.5-0.5B-abliterated 3K huihui-ai/Qwen2.5-0.5B-Instruct-abliterated-v3 1K madhurjindal/Jailbreak-Detector-2-XL 236 Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1 135 thirdeyeai/Qwen2.5-0.5B-Instruct-uncensored 117
Total size
4.70 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-04-06 01:16
Source huggingface.co/arzaan789/qwen2.5-0.5b-uncensored ↗ Base model Qwen/Qwen2.5-0.5B-Instruct ↗

Files by quantization

F16 1 file 948 MB
qwen2.5_0.5b_uncensored.f16.gguf 948 MB 7d24468e download
Q8_0 1 file 506 MB
qwen2.5_0.5b_uncensored.Q8_0.gguf 506 MB d788d996 download
Q6_K 1 file 482 MB
qwen2.5_0.5b_uncensored.Q6_K.gguf 482 MB 162fa40b download
Q5_K 2 files 794 MB
qwen2.5_0.5b_uncensored.Q5_K_M.gguf 401 MB 152427fe download
qwen2.5_0.5b_uncensored.Q5_K_S.gguf 394 MB 7a62fac3 download
Q4_K 2 files 747 MB
qwen2.5_0.5b_uncensored.Q4_K_M.gguf 379 MB 1dd8acd6 download
qwen2.5_0.5b_uncensored.Q4_K_S.gguf 368 MB d79fb586 download
Q3_K 3 files 1014 MB
qwen2.5_0.5b_uncensored.Q3_K_L.gguf 352 MB b5601147 download
qwen2.5_0.5b_uncensored.Q3_K_M.gguf 339 MB 724955be download
qwen2.5_0.5b_uncensored.Q3_K_S.gguf 323 MB 23aa81d6 download
Q2_K 1 file 323 MB
qwen2.5_0.5b_uncensored.Q2_K.gguf 323 MB da26f060 download
Auxiliary files 2 files 3.52 KB
.gitattributes 2.25 KB 424d9097 download
README.md 1.27 KB b66de875 download

README current version from Hugging Face

license: apache-2.0
base_model: Qwen/Qwen2.5-0.5B-Instruct
tags:

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

qwen2.5-0.5b-uncensored

Uncensored variant of Qwen/Qwen2.5-0.5B-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) 0/64
Harmless (64 prompts) 0/64

Usage

llama-cli -m qwen2.5_0.5b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model Qwen/Qwen2.5-0.5B-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. 2026-04-06Upload README.md with huggingface_hub45b304b1.3 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