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

NICKO/gemma-3-27b-it-abliterated-BonfyreFPQ-Native

NICKO Gemma 27B 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-3-27b-it-abliterated-BonfyreFPQ-Native"
Response includes
  • classification m1
  • files 14
  • benchmarks 11 entries
  • 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

Benchmarks

Benchmark Score Source
Entertainment 1.5 UGI
Hazardous 2.4 UGI
Natural Intelligence 29.6 UGI
Political lean -7.7% UGI
Sensitive-Info 20.32 UGI
SocPol 2.4 UGI
UGI 41.05 UGI
Willingness (10) 8.2 UGI
W10-Adherence 7.5 UGI
W10-Direct 9 UGI
Writing 35.62 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
bonfyre-fpq native-format compressed gemma-3 abliterated base_model:mlabonne/gemma-3-27b-it-abliterated base_model:finetune:mlabonne/gemma-3-27b-it-abliterated license:gemma region:us

Related

Total size
0 B
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-01 04:51

Files by quantization

Auxiliary files 14 files 2.99 GB
model-part10.fpq 277 MB 80142988 download
model-part11.fpq 277 MB d91f063e download
model-part4.fpq 277 MB 48a84c36 download
model-part5.fpq 277 MB 5e23ea13 download
model-part6.fpq 277 MB c61f6044 download
model-part7.fpq 277 MB 8c62f331 download
model-part8.fpq 277 MB 028f5b61 download
model-part9.fpq 277 MB 42839972 download
model-part3.fpq 277 MB e4684156 download
model-part2.fpq 277 MB 0d1f14fd download
model-part1.fpq 271 MB ada4c0ab download
model-part12.fpq 25.8 MB ea6ebf16 download
.gitattributes 2.10 KB 8cfa4087 download
README.md 719 B fb31a1c2 download

README current version from Hugging Face


tags: [bonfyre-fpq, native-format, compressed, gemma-3, abliterated]
license: gemma
base_model: mlabonne/gemma-3-27b-it-abliterated

Gemma-3-27B-IT Abliterated — BonfyreFPQ Native Format

mlabonne/gemma-3-27b-it-abliterated compressed into BonfyreFPQ v4.

12 shards totalling ~54 GB BF16 → 3.32 GB FPQ (16.3× actual file ratio, 9.1× FP32-equiv).

File Tensors FPQ Size
model-part1.fpq 460 285 MB
model-part2.fpq–part11.fpq 78 each 277 MB each
model-part12.fpq 7 26 MB
Total 1242 ~3.32 GB

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_hub02773f0719 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