← back to catalog · registered 2026-09-01 10:03

3MPER0RR/gemma-4-12b-it-3MPER0RR-abliterated

3MPER0RR Gemma 12B
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/3MPER0RR%2Fgemma-4-12b-it-3MPER0RR-abliterated"
Response includes
  • classification m1
  • files 14
  • hub_downloads_all_time 280
  • author_summary 37 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
280
73 last 30d - stable
Likes
0
Descendants
2
in 2 direct forks
Model age
6w ago
created 2026-09-01
Downloads over time
Now306→from0↑0%
01122243370 on Sep 1306 on Oct 17306 on Oct 16SepOct
Sep 1 → Oct 17 · 47 snapshots · spans 46 days

Genealogy 2 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

Tags
safetensors gemma4_unified image-text-to-text conversational base_model:google/gemma-4-12B-it base_model:finetune:google/gemma-4-12B-it license:apache-2.0 region:us

Related

Total size
22.3 GB
Files
14
Quantizations
1
Registered
2026-09-01 10:03
Last updated on HF
2026-09-20 09:36

Files by quantization

Auxiliary files 14 files 22.3 GB
model-00004-of-00005.safetensors 4.64 GB f2387d98 download
model-00002-of-00005.safetensors 4.63 GB 66a94870 download
model-00001-of-00005.safetensors 4.62 GB a813e9d9 download
model-00003-of-00005.safetensors 4.55 GB fc175615 download
model-00005-of-00005.safetensors 3.84 GB c83f08c6 download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 64.8 KB 752efb73 download
chat_template.jinja 18.2 KB 4741bf6e download
config.json 4.84 KB 5d67fb1a download
tokenizer_config.json 3.65 KB bc3271ed download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.35 KB b889adcd download
generation_config.json 255 B da32640a download
README.md 60.0 B b289d603 download

README current version from Hugging Face


license: apache-2.0
pipeline_tag: image-text-to-text

README history 4 versions

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

  1. 2026-09-20Update README.md94bfeb2305 B
    Loading...
  2. 2026-09-05Update README.md401c0ab269 B
    Loading...
  3. 2026-09-01Update README.md3a8c5c460 B
    Loading...
  4. 2026-09-01Create README.mdcffa48e27 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