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

Pew404/Qwen2.5-3B-Instruct-abliterated

Pew404 Qwen 3.4B
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/Pew404%2FQwen2.5-3B-Instruct-abliterated"
Response includes
  • classification m1
  • files 13
  • benchmarks 5 entries
  • hub_downloads_all_time 105
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
105
23 last 30d - stable
Likes
0
Model age
19mo ago
created 2025-03-04
Downloads over time
Now116→from24↑383%
0428512724 on Mar 5, 2025116 on Oct 11116 on Oct 8Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 5, 2025 → Oct 11 · 123 snapshots · spans 585 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 0.42884939680892464 OpenLLM-v2
IFEval instruct 0.6942446043165468 OpenLLM-v2
IFEval-Prompt 0.600739371534196 OpenLLM-v2
MATH lvl 5 0 OpenLLM-v2
MMLU-Pro 0.3254654255319149 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/Qwen2.5-3B-Instruct this lineage
Pew404/Qwen2.5-3B-Instruct-abliterated↓ 23

Metadata

License
mit
Languages
zho eng fra spa por deu ita rus jpn kor vie tha ara
Tags
transformers safetensors qwen2 text-generation conversational zho eng fra spa por deu ita

Related

Same base model
arzaan789/qwen2.5-3b-uncensored 1K Goekdeniz-Guelmez/Josiefied-Qwen2.5-3B-Instruct-abliterated-v1 780 zemelee/qwen2.5-jailbreak 471 kikichi/Qwen2.5-3B-Instruct-Uncensored 378 Bender1011001/Qwen2.5-3B-Instruct-ABLITERATED 198
Total size
6.33 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-29 08:45
Source huggingface.co/Pew404/Qwen2.5-3B-Instruct-abliterated ↗ Base model Qwen/Qwen2.5-3B-Instruct ↗

Files by quantization

Auxiliary files 13 files 6.34 GB
model-00001-of-00002.safetensors 4.62 GB 7cbcd09c download
model-00002-of-00002.safetensors 1.71 GB 75ad7ea1 download
tokenizer.json 10.9 MB 63a2951d download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 34.8 KB 71e932e2 download
tokenizer_config.json 7.16 KB 384b8ae2 download
.gitattributes 1.53 KB 52373fe2 download
README.md 865 B a8f47633 download
config.json 731 B 0c5abd03 download
added_tokens.json 605 B 482ced46 download
special_tokens_map.json 496 B aa59b333 download
generation_config.json 243 B 293b20f1 download

README current version from Hugging Face

library_name: transformers
license: mit
language:

  • zho
  • eng
  • fra
  • spa
  • por
  • deu
  • ita
  • rus
  • jpn
  • kor
  • vie
  • tha
  • ara
    base_model:
  • Qwen/Qwen2.5-3B-Instruct
    pipeline_tag: text-generation

Model Card for Model ID

Qwen2.5-3B-Instruct-Abliterated

Model Sources [optional]

Uses

有限资VRAM资源的场景使用NSFW RolePlay或其他需要Uncensored模型的场景

README history 8 versions

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

  1. 2025-04-29Improve language tag (#1)29048f2830 B
    Loading...
  2. 2025-03-05Update README.mdf9a0f9e772 B
    Loading...
  3. 2025-03-05Update README.md05920a8669 B
    Loading...
  4. 2025-03-04Upload Qwen2ForCausalLMb5d92395.1 KB
    Loading...
  5. 2025-03-04Update README.md952ff9b796 B
    Loading...
  6. 2025-03-04Update README.mdd4ef3ef728 B
    Loading...
  7. 2025-03-04Update README.md4fa919a729 B
    Loading...
  8. 2025-03-04Create README.md36e42e3119 B
    Loading...

Discussions 1 thread

  1. 2025-04-28PRImprove language tagmerged2 💬#1
    Loading...

Continue on Hugging Face →

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