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

mradermacher/gemma-3-1b-it-abliterated-GGUF

mradermacher Gemma 1B GGUF second-order 33K 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/mradermacher%2Fgemma-3-1b-it-abliterated-GGUF"
Response includes
  • classification m8
  • files 14
  • hub_downloads_all_time 6,410
  • author_summary 3324 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 layer-wise ablation 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='huihui-ai/gemma-3-1b-it-abliterated' (base is huihui-ai model (M3))
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
6K
428 last 30d - cooling
Likes
1
Model age
19mo ago
created 2025-03-20
Downloads over time
Now6.5K→from453↑1,331%
1522.5K4.8K7.1K453 on Mar 19, 20256.5K on Oct 11Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 19, 2025 → Oct 11 · 121 snapshots · spans 571 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 · 954 downloads combined

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

Metadata

License
gemma
Languages
en
Quantizations
F16 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf chat abliterated uncensored en base_model:huihui-ai/gemma-3-1b-it-abliterated base_model:quantized:huihui-ai/gemma-3-1b-it-abliterated license:gemma endpoints_compatible region:us conversational

Related

Total size
10.2 GB
Files
14
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2025-07-31 08:09

Files by quantization

F16 1 file 1.87 GB
gemma-3-1b-it-abliterated.f16.gguf 1.87 GB de581568 download
Q8_0 1 file 1020 MB
gemma-3-1b-it-abliterated.Q8_0.gguf 1020 MB c93f7aa3 download
Q6_K 1 file 965 MB
gemma-3-1b-it-abliterated.Q6_K.gguf 965 MB e1178c2b download
Q5_K 2 files 1.57 GB
gemma-3-1b-it-abliterated.Q5_K_M.gguf 812 MB 266f2f5a download
gemma-3-1b-it-abliterated.Q5_K_S.gguf 798 MB e11c3470 download
Q4_K 2 files 1.48 GB
gemma-3-1b-it-abliterated.Q4_K_M.gguf 769 MB 2c93e18b download
gemma-3-1b-it-abliterated.Q4_K_S.gguf 745 MB 92a3a020 download
Q3_K 3 files 2.01 GB
gemma-3-1b-it-abliterated.Q3_K_L.gguf 717 MB f0c27eb5 download
gemma-3-1b-it-abliterated.Q3_K_M.gguf 689 MB 777d233c download
gemma-3-1b-it-abliterated.Q3_K_S.gguf 657 MB cbdc0757 download
IQ4 1 file 685 MB
gemma-3-1b-it-abliterated.IQ4_XS.gguf 685 MB 8c60f0ad download
Q2_K 1 file 658 MB
gemma-3-1b-it-abliterated.Q2_K.gguf 658 MB 4f0f3702 download
Auxiliary files 2 files 6.24 KB
README.md 3.90 KB 09d05259 download
.gitattributes 2.34 KB 795fbde0 download

README current version from Hugging Face


base_model: huihui-ai/gemma-3-1b-it-abliterated
extra_gated_button_content: Acknowledge license
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
Face and click below. Requests are processed immediately.
language:

  • en
    library_name: transformers
    license: gemma
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • chat
  • abliterated
  • uncensored

About

static quants of https://huggingface.co/huihui-ai/gemma-3-1b-it-abliterated

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-3-1b-it-abliterated-i1-GGUF

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 Q3_K_S 0.8
GGUF Q2_K 0.8
GGUF IQ4_XS 0.8
GGUF Q3_K_M 0.8 lower quality
GGUF Q3_K_L 0.9
GGUF Q4_K_S 0.9 fast, recommended
GGUF Q4_K_M 0.9 fast, recommended
GGUF Q5_K_S 0.9
GGUF Q5_K_M 1.0
GGUF Q6_K 1.1 very good quality
GGUF Q8_0 1.2 fast, best quality
GGUF f16 2.1 16 bpw, overkill

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.

README history 5 versions

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

  1. 2025-07-31auto-patch README.mdc104b5b3.9 KB
    Loading...
  2. 2025-07-11auto-patch README.md1fcae684.1 KB
    Loading...
  3. 2025-07-10auto-patch README.md8601f824.1 KB
    Loading...
  4. 2025-03-20auto-patch README.mdaffe8dd3.9 KB
    Loading...
  5. 2025-03-20uploaded from nico17c42ed1225 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