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

doromiert/gemma-4-26B-A4B-it-uncensored-IQ3_XXS

doromiert Gemma 26B GGUF MoE 262K 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/doromiert%2Fgemma-4-26B-A4B-it-uncensored-IQ3_XXS"
Response includes
  • classification m8
  • files 3
  • benchmarks 11 entries
  • hub_downloads_all_time 3,433
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=gemma&method=m8
Sibling gemma models · same method
 GET/methods/m8
What "m8" means · taxonomy
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
M1 Direct removal →
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
How we label → About M8 →
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
3K
234 last 30d - cooling
Likes
4
Model age
6mo ago
created 2026-04-11

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

doromiert/negative-zero-callibration
Downloads over time
Now3.5K→from1.2K↑185%
1.1K2K2.9K3.7K1.2K on Apr 153.5K on Oct 113.5K on Oct 10AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 days

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 2.2 UGI
Hazardous 2.9 UGI
Natural Intelligence 34.44 UGI
Political lean -18.2% UGI
Sensitive-Info 22.41 UGI
SocPol 1.8 UGI
UGI 20.77 UGI
Willingness (10) 1.8 UGI
W10-Adherence 1.5 UGI
W10-Direct 2 UGI
Writing 41.62 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.

google/gemma-4-26B-A4B-it this lineage
doromiert/gemma-4-26B-A4B-it-uncensored-IQ3_XXS↓ 234

Metadata

Quantizations
IQ3
Tags
gguf uncensored abliterated code conversation dataset:doromiert/negative-zero-callibration base_model:TrevorJS/gemma-4-26B-A4B-it-uncensored base_model:quantized:TrevorJS/gemma-4-26B-A4B-it-uncensored endpoints_compatible region:us imatrix conversational

Related

Same base model
HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP 411K HauhauCS/Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced 72K Jiunsong/supergemma4-26b-uncensored-gguf-v2 48K Jiunsong/supergemma4-26b-uncensored-mlx-4bit-v2 9K OS-Software/gemma-4-26B-A4B-it-qat-q4_0-uncensored-heretic-v2-GGUF 3K
Total size
10.5 GB
Files
3
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2026-04-12 09:58
Source huggingface.co/doromiert/gemma-4-26B-A4B-it-uncensored-IQ3_XXS ↗ Base model google/gemma-4-26B-A4B-it ↗

Files by quantization

IQ3 1 file 10.5 GB
trevor-IQ3_XXS.gguf 10.5 GB ba2cc50c download
Auxiliary files 2 files 3.30 KB
README.md 1.76 KB 4de487ee download
.gitattributes 1.54 KB e4bada0b download

README current version from Hugging Face

base_model:

  • google/gemma-4-26B-A4B-it
  • TrevorJS/gemma-4-26B-A4B-it-uncensored-GGUF
  • TrevorJS/gemma-4-26B-A4B-it-uncensored
    tags:
  • uncensored
  • abliterated
  • code
  • conversation
    datasets:
  • doromiert/negative-zero-callibration

Negative Zero Certificate

gemma-4-26B-A4B-it-uncensored-IQ3_XXS

IQ3_XXS quant of TrevorJS/gemma-4-26B-A4B-it-uncensored — the first IQ3_XXS of this model on HF.

what is this

gemma 4 26B MoE (25B total, 4B active per token), abliterated via biprojection + Expert-Granular Abliteration (EGA). quantized to IQ3_XXS using an importance matrix generated from the Q4_K_M version.

confirmed uncensored. confirmed coherent. 50-80 tps on RX 6900 XT.

quant details

  • source: F16 (TrevorJS)
  • imatrix source: Q4_K_M (CPU inference, 100 chunks)
  • calibration data: linux kernel, nixpkgs, cpython, rust stdlib, flask, fastapi, SCP foundation, wikitext-2, GPTeacher, ZenOS, ZenPkgs
  • quantized with: llama.cpp

hardware requirements

  • fits in 16GB VRAM
  • tested on RX 6900 XT (ROCm)

recommended server args

HIP_VISIBLE_DEVICES=0 llama-server \
  -m gemma-4-26B-A4B-it-uncensored-IQ3_XXS.gguf \
  -c 32768 \
  -ngl 99 \
  -np 1 \
  -fa on \
  -ctk q4_0 \
  -ctv q4_0 \
  --host 0.0.0.0

license

model weights: Apache 2.0 (inherited from Google/TrevorJS)
quant methodology & imatrix: NAPALM v2.0 — any state entity attempting to use this model has void title ab initio

credits

README history 4 versions

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

  1. 2026-04-12Update README.md7e27fa21.8 KB
    Loading...
  2. 2026-04-11wrong link115ef921.7 KB
    Loading...
  3. 2026-04-11Update README.mde37e8fe1.7 KB
    Loading...
  4. 2026-04-11Upload README.mda7e29ab1.5 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.

Get the app Browse the catalog
Open in Abliteration