← back to catalog · registered 2026-11-15 01:03

mradermacher/gemma4-E4B-it-Abliterated-AND-Disinhibited-i1-GGUF

mradermacher GGUF 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/mradermacher%2Fgemma4-E4B-it-Abliterated-AND-Disinhibited-i1-GGUF"
Response includes
  • classification m8
  • files 18
  • author_summary 3602 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
HIGH
Inherited from base model
Why this label 3 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • author=mradermacher (M8 quantization producer, never originator)
  • is_gguf=1
  • base_model='stevenh512/gemma4-E4B-it-Abliterated-AND-Disinhibited' (base has 'abliterated' marker, assume M1 default)
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 · 30-day
10K
Likes
1
Model age
1w ago
created 2026-11-15
Downloads over time
Now 10K → from 0 ↑ 0%
03.7K7.4K11K 0 on Nov 15 10K on Nov 22 Nov
Nov 15 → Nov 22 · 8 snapshots · spans 7 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.

Variants by this author 2 formats · 12K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
gemma
Languages
en
Quantizations
IQ1 IQ2 IQ3 IQ4 Q2_K Q3_K Q4_K Q6_K
Tags
transformers gguf disinhibition abliteration gemma mechanistic-interpretability alignment en base_model:stevenh512/gemma4-E4B-it-Abliterated-AND-Disinhibited base_model:quantized:stevenh512/gemma4-E4B-it-Abliterated-AND-Disinhibited license:gemma endpoints_compatible

Related

Total size
64.5 GB
Files
18
Quantizations
10
Registered
2026-11-15 01:03
Last updated on HF
2026-11-21 12:07

Files by quantization

Q6_K 1 file 5.75 GB
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-Q6_K.gguf 5.75 GB 7ae65714 download
Q4_K 2 files 9.75 GB
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-Q4_K_M.gguf 4.94 GB 61c47ac8 download
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-Q4_K_S.gguf 4.82 GB 03ec1369 download
IQ4 2 files 9.50 GB
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-IQ4_NL.gguf 4.81 GB 2a2b9dc8 download
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-IQ4_XS.gguf 4.69 GB d0f66e14 download
Q3_K 3 files 13.5 GB
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-Q3_K_L.gguf 4.65 GB 5353aded download
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-Q3_K_M.gguf 4.49 GB 4d1cee49 download
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-Q3_K_S.gguf 4.31 GB 8c47d95f download
IQ3 2 files 8.07 GB
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-IQ3_M.gguf 4.37 GB 2c108785 download
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-IQ3_XXS.gguf 3.71 GB 3d46f66b download
Q2_K 2 files 8.05 GB
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-Q2_K.gguf 4.08 GB 6c77389f download
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-Q2_K_S.gguf 3.98 GB ba894ebc download
IQ2 2 files 6.80 GB
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-IQ2_M.gguf 3.53 GB c2c75597 download
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-IQ2_XXS.gguf 3.27 GB 7076a779 download
IQ1 1 file 3.14 GB
gemma4-E4B-it-Abliterated-AND-Disinhibited.i1-IQ1_M.gguf 3.14 GB d2a0f15e download
Drafts and companions 1 file 8.46 MB
gemma4-E4B-it-Abliterated-AND-Disinhibited.imatrix.gguf 8.46 MB e0c7afa3 download
Auxiliary files 2 files 6.06 KB
README.md 3.12 KB 0da74199 download
.gitattributes 2.95 KB 156bb570 download

README current version from Hugging Face


base_model: stevenh512/gemma4-E4B-it-Abliterated-AND-Disinhibited
language:

  • en
    library_name: transformers
    license: gemma
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • disinhibition
  • abliteration
  • gemma
  • mechanistic-interpretability
  • alignment

About

weighted/imatrix quants of https://huggingface.co/stevenh512/gemma4-E4B-it-Abliterated-AND-Disinhibited

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/gemma4-E4B-it-Abliterated-AND-Disinhibited-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs
for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF imatrix 0.1 imatrix file (for creating your own quants)
GGUF i1-Q2_K 4.5 IQ3_XXS probably better
GGUF i1-IQ3_M 4.8

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

README history 6 versions

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

  1. 2026-11-21 auto-patch README.md 5859689 7.4 KB
    Loading...
  2. 2026-11-20 auto-patch README.md 5e47650 7.3 KB
    Loading...
  3. 2026-11-15 auto-patch README.md 3999fc8 7.4 KB
    Loading...
  4. 2026-11-15 auto-patch README.md 025b783 6.1 KB
    Loading...
  5. 2026-11-15 auto-patch README.md 8e74c4a 3.1 KB
    Loading...
  6. 2026-11-15 uploaded from leia e9af02d 499 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