← back to catalog · registered 2026-11-11 02:03

jsantillana/Qwen2.5-Coder-32B-Instruct-abliterated-v3-GGUF

jsantillana 32B 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/jsantillana%2FQwen2.5-Coder-32B-Instruct-abliterated-v3-GGUF"
Response includes
  • classification m8
  • files 5
  • author_summary 26 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
166
Likes
0
Model age
1w ago
created 2026-11-11
Downloads over time
Now 166 → from 0 ↑ 0%
061122183 0 on Nov 11 166 on Nov 22 166 on Nov 20 Nov
Nov 11 → Nov 22 · 12 snapshots · spans 11 days

Variants by this author 2 formats · 423 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
other
Quantizations
Q3_K Q4_K Q8_0
Tags
gguf abliteration cybersecurity research license:other endpoints_compatible region:us conversational

Related

Total size
65.8 GB
Files
5
Quantizations
4
Registered
2026-11-11 02:03
Last updated on HF
2026-11-11 02:04

Files by quantization

Q8_0 1 file 32.4 GB
Qwen2.5-Coder-32B-Instruct-abliterated-fix3-Q8_0.gguf 32.4 GB df776168 download
Q4_K 1 file 18.5 GB
Qwen2.5-Coder-32B-Instruct-abliterated-fix3-Q4_K_M.gguf 18.5 GB 52e47e36 download
Q3_K 1 file 14.8 GB
Qwen2.5-Coder-32B-Instruct-abliterated-fix3-Q3_K_M.gguf 14.8 GB 063d2928 download
Auxiliary files 2 files 2.49 KB
.gitattributes 1.75 KB b22420fb download
README.md 758 B 898e3507 download

README current version from Hugging Face


license: other
license_name: apache-2.0-restricted-research
tags:

  • abliteration
  • gguf
  • cybersecurity
  • research

Qwen2.5-Coder-32B-Instruct Abliterated Fix3 — GGUF

⚠️ Defensive security research only. Abliterated model: will comply with requests the
base refuses. Not for production. Authors not responsible for misuse.

Parent repo with full model card, methodology and evals:
jsantillana/Qwen2.5-Coder-32B-Instruct-abliterated-v3

Quantizations

| Qwen2.5-Coder-32B-Instruct-abliterated-fix3-Q3_K_M.gguf | — |
| Qwen2.5-Coder-32B-Instruct-abliterated-fix3-Q4_K_M.gguf | — |
| Qwen2.5-Coder-32B-Instruct-abliterated-fix3-Q8_0.gguf | — |

README history 1 version

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

  1. 2026-11-11 Upload README.md with huggingface_hub faed007 758 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