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

criscarleo/qwen2.5-coder-3b-abliterated-basic

criscarleo Qwen 3B GGUF
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/criscarleo%2Fqwen2.5-coder-3b-abliterated-basic"
Response includes
  • classification m8
  • files 15
  • author_summary 6 models
  • readme_text full
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
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
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 · 30-day
23
↑ 172% in 90 days
Likes
0
Model age
6mo ago
created 2026-03-23
Downloads over time
Now484→from178↑172%
163280397515178 on Mar 25484 on Aug 31MarAprMayJunJulAug
Mar 25 → Aug 31 · 27 snapshots · spans 159 days

Metadata

License
agpl-3.0
Tags
safetensors gguf qwen2 license:agpl-3.0 endpoints_compatible region:us conversational

Related

Total size
11.5 GB
Files
15
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-30 22:40

Files by quantization

Auxiliary files 15 files 11.5 GB
qwen2.5-coder-3b-abliterated-basic.gguf 5.75 GB 7a917af0 download
model-00001-of-00004.safetensors 1.83 GB bbdc3c29 download
model-00003-of-00004.safetensors 1.82 GB 79042a31 download
model-00002-of-00004.safetensors 1.82 GB ac13a7a9 download
model-00004-of-00004.safetensors 276 MB 2c01fb7e download
tokenizer.json 10.9 MB 3fd16973 download
vocab.json 2.94 MB 316bb6c8 download
model.safetensors.index.json 34.8 KB 812c2009 download
chat_template.jinja 2.45 KB bdf7919a download
abliteration_metadata.json 1.80 KB 60625a89 download
.gitattributes 1.61 KB 0c3bddd1 download
config.json 1.51 KB 8771c6a7 download
README.md 742 B aa8e4373 download
tokenizer_config.json 692 B 1a3d9af9 download
generation_config.json 138 B 2cbf46ec download

README current version from Hugging Face


license: agpl-3.0

Method & Process

This model was processed using the Obliteratus methodology.
The fine-tuning/transformation was executed via the official notebook provided by [pliny-the-prompter](https://huggingface.co/spaces/pliny-the-prompter/obliteratus

Quantization & Inference Engine

  • Framework: llama.cpp
  • Format: GGUF (v3)
  • Original Authors: Georgi Gerganov and the GGML contributors.

References & Credits

README history 1 version

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

  1. 2026-03-30Create README.md734f7c6742 B
    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.

Open in Abliteration