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

NICKO/gemma-3-12b-it-abliterated-BonfyreFPQ-Native

NICKO Gemma 12B second-order
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/NICKO%2Fgemma-3-12b-it-abliterated-BonfyreFPQ-Native"
Response includes
  • classification m1
  • files 7
  • author_summary 7 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 · 30-day
0
Likes
0
Model age
4mo ago
created 2026-06-01
Downloads over time
Now0→from0↑0%
00110 on Jun 100 on Oct 12JunJulAugSepOct
Jun 10 → Oct 12 · 58 snapshots · spans 124 days

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
bonfyre-fpq native-format compressed gemma-3 abliterated base_model:mlabonne/gemma-3-12b-it-abliterated base_model:finetune:mlabonne/gemma-3-12b-it-abliterated license:gemma region:us

Related

Total size
0 B
Files
7
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-01 03:49

Files by quantization

Auxiliary files 7 files 1.33 GB
model-part1.fpq 278 MB 390cde6c download
model-part3.fpq 276 MB ac9f7560 download
model-part4.fpq 276 MB 0b1f0e49 download
model-part2.fpq 276 MB 0ddb57b0 download
model-part5.fpq 257 MB ba358722 download
.gitattributes 1.74 KB 1d1746fe download
README.md 851 B 425e5593 download

README current version from Hugging Face


tags: [bonfyre-fpq, native-format, compressed, gemma-3, abliterated]
license: gemma
base_model: mlabonne/gemma-3-12b-it-abliterated

Gemma-3-12B-IT Abliterated — BonfyreFPQ Native Format

mlabonne/gemma-3-12b-it-abliterated compressed into BonfyreFPQ v4.

File Tensors BF16 Source FPQ Size Ratio
model-part1.fpq 500 ~4.64 GB 292 MB ~16.3×
model-part2.fpq 143 ~4.59 GB 289 MB ~16.3×
model-part3.fpq 143 ~4.59 GB 289 MB ~16.3×
model-part4.fpq 143 ~4.59 GB 289 MB ~16.3×
model-part5.fpq 136 ~4.29 GB 270 MB ~16.3×
Total 1065 ~22.7 GB 1.43 GB ~15.9×

FPQ v4 | COORD@3+QJL | 3.50 avg bpw | 9.1× FP32-equiv ratio

README history 1 version

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

  1. 2026-06-01Upload README.md with huggingface_hubfefaae1851 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