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

arzaan789/qwen2.5-1.5b-uncensored

arzaan789 Qwen 1.5B 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%2Fqwen2.5-1.5b-uncensored"
Response includes
  • classification m8
  • files 13
  • benchmarks 16 entries
  • hub_downloads_all_time 2,495
  • 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
1K last 30d - stable
Likes
1
Model age
6mo ago
created 2026-04-06
Downloads over time
Now3.1K→from284↑991%
1431.2K2.3K3.4K284 on Apr 153.1K on Oct 12AprMayJunJulAugSepOct
Apr 15 → Oct 12 · 66 snapshots · spans 180 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 0.39278765079776884 OpenLLM-v2
IFEval instruct 0.4940047961630696 OpenLLM-v2
IFEval-Prompt 0.4011090573012939 OpenLLM-v2
MATH lvl 5 0.01283987915407855 OpenLLM-v2
MMLU-Pro 0.27992021276595747 OpenLLM-v2
Entertainment 0.9 UGI
Hazardous 1.8 UGI
Natural Intelligence 8.66 UGI
Political lean -12.1% UGI
Sensitive-Info 9.9 UGI
SocPol 0.5 UGI
UGI 14.93 UGI
Willingness (10) 2.5 UGI
W10-Adherence 2 UGI
W10-Direct 3 UGI
Writing 22.17 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/Qwen2.5-1.5B-Instruct this lineage
arzaan789/qwen2.5-1.5b-uncensored↓ 1,112

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/Qwen2.5-1.5B-Instruct base_model:quantized:Qwen/Qwen2.5-1.5B-Instruct license:apache-2.0 endpoints_compatible region:us

Related

Other by arzaan789
phi-4-mini-uncensored 1K qwen2.5-3b-uncensored 1K qwen3.5-4b-uncensored 907 smolm3-3b-uncensored 878 qwen2.5-0.5b-uncensored 798
Same base model
DeKodez/Qwen2.5-1.5B-Instruct-abliterated 429 ElementMerc/qwen2.5-1.5b-abliterated 257 sbussiso/Qwen2.5-1.5B-abliterated 244 ops-malware/qwen2.5-1.5b-abliterated 238 jaswanthsanjay88/Qwen2.5-1.5B-Abliterated 90
Total size
12.4 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-04-06 02:24
Source huggingface.co/arzaan789/qwen2.5-1.5b-uncensored ↗ Base model Qwen/Qwen2.5-1.5B-Instruct ↗

Files by quantization

F16 1 file 2.88 GB
qwen2.5_1.5b_uncensored.f16.gguf 2.88 GB a1f60f57 download
Q8_0 1 file 1.53 GB
qwen2.5_1.5b_uncensored.Q8_0.gguf 1.53 GB 19fe8446 download
Q6_K 1 file 1.19 GB
qwen2.5_1.5b_uncensored.Q6_K.gguf 1.19 GB 99b206de download
Q5_K 2 files 2.07 GB
qwen2.5_1.5b_uncensored.Q5_K_M.gguf 1.05 GB 4bc620ad download
qwen2.5_1.5b_uncensored.Q5_K_S.gguf 1.02 GB ba08831c download
Q4_K 2 files 1.79 GB
qwen2.5_1.5b_uncensored.Q4_K_M.gguf 940 MB d83ad6d9 download
qwen2.5_1.5b_uncensored.Q4_K_S.gguf 897 MB 044ab75a download
Q3_K 3 files 2.30 GB
qwen2.5_1.5b_uncensored.Q3_K_L.gguf 839 MB 47307ae3 download
qwen2.5_1.5b_uncensored.Q3_K_M.gguf 786 MB f350b376 download
qwen2.5_1.5b_uncensored.Q3_K_S.gguf 726 MB 88372c61 download
Q2_K 1 file 645 MB
qwen2.5_1.5b_uncensored.Q2_K.gguf 645 MB ca990cf5 download
Auxiliary files 2 files 3.52 KB
.gitattributes 2.25 KB a894cfa5 download
README.md 1.27 KB 0827f491 download

README current version from Hugging Face

license: apache-2.0
base_model: Qwen/Qwen2.5-1.5B-Instruct
tags:

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

qwen2.5-1.5b-uncensored

Uncensored variant of Qwen/Qwen2.5-1.5B-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) 6/64
Harmless (64 prompts) 0/64

Usage

llama-cli -m qwen2.5_1.5b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model Qwen/Qwen2.5-1.5B-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_hub1cca09b1.3 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