← back to catalog · registered 2026-09-12 18:55

lucifer053/gemma-4-12b-it-uncensored-th

lucifer053 Gemma 12B GGUF
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
0
Likes
0
Model age
today
created 2026-09-12
Downloads over time
Now0from0↑0%
00110 on Sep 120 on Sep 13Sep
Sep 12 → Sep 13 · 2 snapshots · spans 1 day

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 1.1 UGI
Hazardous 2.9 UGI
Natural Intelligence 25.81 UGI
Political lean -17.4% UGI
Sensitive-Info 16.56 UGI
SocPol 1.3 UGI
UGI 15.2 UGI
Willingness (10) 1.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 1 UGI
Writing 31.6 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.

Metadata

License
gemma
Languages
th en
Quantizations
F16 Q4_K
Tags
gguf abliterated uncensored thai vision multimodal image-text-to-text th en base_model:google/gemma-4-12B-it base_model:quantized:google/gemma-4-12B-it license:gemma

Related

Total size
29.1 GB
Files
4
Quantizations
3
Registered
2026-09-12 18:55
Last updated on HF
2026-09-12 19:25

Files by quantization

F16 1 file 22.2 GB
gemma-4-12B-it-uncensored-beta1-F16.gguf 22.2 GB de88bcb3 download
Q4_K 1 file 6.87 GB
gemma-4-12B-it-uncensored-beta1-Q4_K_M.gguf 6.87 GB 363b83fd download
Auxiliary files 2 files 3.61 KB
README.md 1.82 KB 6c206b20 download
.gitattributes 1.80 KB 14407083 download

README current version from Hugging Face


license: gemma
base_model: google/gemma-4-12B-it
tags:

  • abliterated
  • uncensored
  • gguf
  • thai
    language:
  • th
  • en
    pipeline_tag: text-generation

Gemma 4 12B Uncensored (Thai + English)

An abliterated (refusal-direction-removed) derivative of
google/gemma-4-12B-it.

This is a modified model derivative created under the Gemma Terms of Use.

What makes this different

Most abliterated models are measured using English-only refusal datasets,
which degrades the model's ability to write in other languages. This model was
abliterated using a Thai + English parallel prompt dataset, so it stays
fluent in Thai while removing over-refusals.

Files

File Size Use case
gemma-4-12B-it-uncensored-beta1-Q4_K_M.gguf ~6.9 GB General use (LM Studio, llama.cpp)
gemma-4-12B-it-uncensored-beta1-F16.gguf ~22.2 GB Full precision / requantizing

How it was made

  • Base model: google/gemma-4-12B-it (dense)
  • Method: abliteration (orthogonalizing the refusal direction out of the weights)
  • Prompt dataset: Thai + English parallel prompts (harmful / harmless pairs).
    Using Thai prompts in the measurement step keeps the model's Thai output natural.
  • Tool: jim-plus/llm-abliteration

Recommended sampling

Abliterated models can loop if the temperature is too low. Recommended settings:

--temp 0.6 --repeat-penalty 1.3 --repeat-last-n 512

Do not drop the temperature below ~0.6.

License & responsible use

Use is subject to the Gemma Terms of Use.
Removing refusals does not remove your responsibility — the prohibited-use
policy still applies. Do not use this model for illegal or harmful activity.

README history 2 versions

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

  1. 2026-09-12Upload README.md with huggingface_hub0e7f27a2.7 KB
    Loading...
  2. 2026-09-12Upload README.md with huggingface_hubf6479cc1.8 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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.