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

ccharnkij/gemma-4-31B-it-Uncensored

ccharnkij Gemma 31B multimodal
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/ccharnkij%2Fgemma-4-31B-it-Uncensored"
Response includes
  • classification m-uncensored
  • files 11
  • benchmarks 11 entries
  • hub_downloads_all_time 33
  • author_summary 20 models
  • readme_text full
Try next
GET/models?author=ccharnkij
All 20 models by ccharnkij
 GET/models?family=gemma&method=m-uncensored
Sibling gemma models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
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
How we label → About M-U →
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
33
Likes
0
Model age
2mo ago
created 2026-08-04
Downloads over time
Now47→from9↑422%
72236519 on Aug 547 on Oct 11AugSepOct
Aug 5 → Oct 11 · 50 snapshots · spans 67 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
Entertainment 1.9 UGI
Hazardous 0 UGI
Natural Intelligence 34.36 UGI
Political lean -19.4% UGI
Sensitive-Info 19.81 UGI
SocPol 3.7 UGI
UGI 21.54 UGI
Willingness (10) 2.5 UGI
W10-Adherence 3 UGI
W10-Direct 2 UGI
Writing 38.57 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.

google/gemma-4-31B-it this lineage
ccharnkij/gemma-4-31B-it-Uncensored↓ 31

Variants by this author 2 formats · 577 downloads combined

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

Metadata

License
apache-2.0
Languages
en
Tags
safetensors gemma4 uncensored text-generation image-text-to-text multimodal reasoning lora conversational en base_model:google/gemma-4-31B-it base_model:adapter:google/gemma-4-31B-it

Related

Other by ccharnkij
Qwen3.5-9B-Uncensored-GGUF 3K Ministral-3-14B-Reasoning-2512-Uncensored-GGUF 2K gpt-oss-120b-Uncensored-GGUF 636 Gemma-4-E4B-it-Uncensored-GGUF 555 gemma-4-31B-it-Uncensored-GGUF 546
Same base model
wangzhang/gemma-4-31B-it-abliterated 301K paperscarecrow/Gemma-4-31B-it-abliterated 143K HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP 96K OS-Software/gemma-4-31B-it-qat-q4_0-uncensored-heretic-GGUF 6K LiconStudio/Gemma-4-31B-it-abliterated-GGUF 6K
Total size
58.3 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-04 02:47
Source huggingface.co/ccharnkij/gemma-4-31B-it-Uncensored ↗ Base model google/gemma-4-31B-it ↗

Files by quantization

Auxiliary files 11 files 58.3 GB
model-00001-of-00002.safetensors 46.4 GB 8f5e699c download
model-00002-of-00002.safetensors 11.9 GB 03b7b226 download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 117 KB 17fcef4a download
tokenizer_config.json 9.15 KB 1ddd4014 download
config.json 5.48 KB 873b56c9 download
chat_template.jinja 2.32 KB 582bb4df download
README.md 2.01 KB e12a36f4 download
processor_config.json 1.65 KB 5465974d download
.gitattributes 1.53 KB 52373fe2 download
generation_config.json 203 B edda3c19 download

README current version from Hugging Face

license: apache-2.0
base_model: google/gemma-4-31B-it
tags:

  • gemma4
  • uncensored
  • text-generation
  • image-text-to-text
  • multimodal
  • reasoning
  • lora
    language:
  • en
    pipeline_tag: image-text-to-text

gemma-4-31B-it-Uncensored

A fine-tuned version of gemma-4-31B-it with uncensored responses. This model removes the default safety filters and restrictions, allowing for more open-ended and unrestricted conversations including adult content.

Model Details

  • Base Model: google/gemma-4-31B-it
  • Fine-tuning Method: LoRA (Low-Rank Adaptation)
  • Model Format: Safetensors
  • Modalities: Text + Images
  • License: Apache 2.0

What's Different

  • Removed refusal behaviors and safety filters
  • Capable of generating adult content
  • Responds to prompts the base model would typically decline

ℹ️ Notes on Uncensoring

This model is zero-shot uncensored but not 100% guaranteed, especially with thinking enabled. Occasionally the model may still produce a refusal depending on the prompt. If this happens, simply regenerate. For best results:

  • Start fresh chat for sensitive topics
  • Don't mix sensitive topic with mundane topics

Non-thinking seems to produce better results than thinking.

GGUF Version

A quantized GGUF version of this model is also available for use with llama.cpp, Ollama, and text-generation-webui:
👉 gemma-4-31B-it-Uncensored-GGUF

💬 Feedback

If you use this model, I'd love to hear from you! Feel free to:

  • Leave a comment on this model page
  • Open a discussion for questions or suggestions
  • Report any issues or unexpected behaviors

Your feedback helps improve future versions.

⚠️ Disclaimer

This model is intended for research and educational purposes only.

License

This model is licensed under the Apache 2.0 License.

README history 1 version

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

  1. 2026-08-04Upload folder using huggingface_hub1c465672 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