← back to catalog · registered 2026-10-06 03:58

Magnarks/gemma-4-12B-it-abliterated-uncensored-nvfp4

Magnarks Gemma 12B 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/Magnarks%2Fgemma-4-12B-it-abliterated-uncensored-nvfp4"
Response includes
  • classification m-uncensored
  • files 2
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
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
347
Likes
0
Model age
6w ago
created 2026-10-06
Downloads over time
Now 2.7K → from 0 ↑ 0%
09972K3K 0 on Oct 6 2.7K on Nov 22 OctNov
Oct 6 → Nov 22 · 48 snapshots · spans 47 days

Metadata

Tags
gguf nvfp4 gemma4 gemma4-12b 12B llama.cpp abliterated uncensored multilingual base_model:OpenYourMind/gemma-4-12B-it-abliterated-uncensored base_model:quantized:OpenYourMind/gemma-4-12B-it-abliterated-uncensored license:gemma
Total size
0 B
Files
2
Quantizations
1
Registered
2026-10-06 03:58
Last updated on HF
2026-10-13 04:53

Files by quantization

Auxiliary files 2 files 1.64 KB
.gitattributes 1.48 KB a6344aac download
README.md 156 B bb724d27 download

README current version from Hugging Face


license: gemma
language:

  • en
  • es
    base_model:
  • OpenYourMind/gemma-4-12B-it-abliterated-uncensored
    tags:
  • nvfp4
  • gguf
  • gemma4
  • gemma4-12b
  • 12B

README history 14 versions

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

  1. 2026-10-13 Aclaración modelos Base 73fb1a1 6.6 KB
    Loading...
  2. 2026-10-13 Fix enlace 8f9bb9a 6.5 KB
    Loading...
  3. 2026-10-13 Actualización enlace 116f392 6.5 KB
    Loading...
  4. 2026-10-13 Aclaración de pruebas y nueva versión del modelo en NVFP4 subida. c1eb110 6.5 KB
    Loading...
  5. 2026-10-06 Actualizados tamaños de los modelos (pronto tabla completa) 1cce9a2 5.8 KB
    Loading...
  6. 2026-10-06 cambiando soporte de idiomas 3725eb5 5.8 KB
    Loading...
  7. 2026-10-06 Cambiando fuente para descarga b89ed9c 5.8 KB
    Loading...
  8. 2026-10-06 Cambiando fuente para descarga c2c488e 5.8 KB
    Loading...
  9. 2026-10-06 Complementando README f0cf185 5.8 KB
    Loading...
  10. 2026-10-06 Complementando README f615215 5.8 KB
    Loading...
  11. 2026-10-06 Update README.md 75d8f92 156 B
    Loading...
  12. 2026-10-06 Update README.md 3005869 156 B
    Loading...
  13. 2026-10-06 initial commit a011b9c 23 B
    Loading...
  14. 2026-10-06 initial commit 31ef478 23 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