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

FORNAX20/gemma-3-12b-it-norm-preserved-biprojected-abliterated-Q6_K-GGUF

FORNAX20 Gemma 12B GGUF multimodal second-order 131K ctx
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/FORNAX20%2Fgemma-3-12b-it-norm-preserved-biprojected-abliterated-Q6_K-GGUF"
Response includes
  • classification m8
  • files 3
  • benchmarks 11 entries
  • hub_downloads_all_time 353
  • author_summary 4 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 · lifetime
353
32 last 30d - cooling
Likes
0
Model age
8mo ago
created 2026-02-10
Downloads over time
Now369→from48↑669%
3215527840148 on Feb 11369 on Oct 11369 on Oct 9FebAprJunAugOct
Feb 11 → Oct 11 · 74 snapshots · spans 242 days

Benchmarks

Benchmark Score Source
Entertainment 0.9 UGI
Hazardous 2.4 UGI
Natural Intelligence 21.33 UGI
Political lean -6.4% UGI
Sensitive-Info 13.89 UGI
SocPol 1.2 UGI
UGI 40.09 UGI
Willingness (10) 9.2 UGI
W10-Adherence 9.5 UGI
W10-Direct 9 UGI
Writing 30.43 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
Tags
transformers gguf llama-cpp gguf-my-repo image-text-to-text base_model:grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated base_model:quantized:grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated license:gemma endpoints_compatible region:us

Related

Total size
9.00 GB
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-02-10 21:40

Files by quantization

Auxiliary files 3 files 9.00 GB
gemma-3-12b-it-norm-preserved-biprojected-abliterated-q6_k.gguf 9.00 GB 8e3f854b download
README.md 2.60 KB fb73a2fe download
.gitattributes 1.58 KB a70e1310 download

README current version from Hugging Face


license: gemma
library_name: transformers
pipeline_tag: image-text-to-text
base_model: grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated
model_index:

  • name: gemma-3-12b-it-norm-preserved-biprojected-abliterated
    results:
    • task:
      type: text-generation
      name: Text Generation
      dataset:
      name: MMLU (5-shot)
      type: cais/mmlu
      config: main
      split: test
      args:
      num_few_shot: 5

      metrics:
      • type: acc
        value: 0.6985
        name: accuracy
        source:
        url: N/A
        name: N/A

tags:

  • llama-cpp
  • gguf-my-repo

FORNAX20/gemma-3-12b-it-norm-preserved-biprojected-abliterated-Q6_K-GGUF

This model was converted to GGUF format from grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo FORNAX20/gemma-3-12b-it-norm-preserved-biprojected-abliterated-Q6_K-GGUF --hf-file gemma-3-12b-it-norm-preserved-biprojected-abliterated-q6_k.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo FORNAX20/gemma-3-12b-it-norm-preserved-biprojected-abliterated-Q6_K-GGUF --hf-file gemma-3-12b-it-norm-preserved-biprojected-abliterated-q6_k.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo FORNAX20/gemma-3-12b-it-norm-preserved-biprojected-abliterated-Q6_K-GGUF --hf-file gemma-3-12b-it-norm-preserved-biprojected-abliterated-q6_k.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo FORNAX20/gemma-3-12b-it-norm-preserved-biprojected-abliterated-Q6_K-GGUF --hf-file gemma-3-12b-it-norm-preserved-biprojected-abliterated-q6_k.gguf -c 2048

README history 1 version

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

  1. 2026-02-10Upload README.md with huggingface_hub4bc2c892.6 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.

Open in Abliteration