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

mradermacher/Gemma-The-Writer-9B-abliterated-GGUF

mradermacher Gemma 9B GGUF second-order 8K 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-The-Writer-9B-abliterated-GGUF"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 5,150
  • 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 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='Naphula/Gemma-The-Writer-9B-abliterated' (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 · lifetime
5K
501 last 30d - cooling
Likes
2
Model age
10mo ago
created 2025-11-24
Downloads over time
Now5.3K→from620↑751%
3872.2K4K5.7K620 on Nov 26, 20255.3K on Oct 11Nov '25JanMarMayJulSep
Nov 26, 2025 → Oct 11 · 85 snapshots · spans 319 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
Languages
en
Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf creative creative writing fiction writing plot generation sub-plot generation story generation scene continue storytelling fiction story science fiction

Related

Total size
72.9 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2025-11-27 02:11

Files by quantization

F16 1 file 17.2 GB
Gemma-The-Writer-9B-abliterated.f16.gguf 17.2 GB 07b23aa1 download
Q8_0 1 file 9.15 GB
Gemma-The-Writer-9B-abliterated.Q8_0.gguf 9.15 GB 864b725f download
Q6_K 1 file 7.07 GB
Gemma-The-Writer-9B-abliterated.Q6_K.gguf 7.07 GB e9a99377 download
Q5_K 2 files 12.2 GB
Gemma-The-Writer-9B-abliterated.Q5_K_M.gguf 6.19 GB b8570144 download
Gemma-The-Writer-9B-abliterated.Q5_K_S.gguf 6.04 GB 463827fd download
Q4_K 2 files 10.5 GB
Gemma-The-Writer-9B-abliterated.Q4_K_M.gguf 5.37 GB edb03e36 download
Gemma-The-Writer-9B-abliterated.Q4_K_S.gguf 5.10 GB f78521b1 download
Q3_K 3 files 13.3 GB
Gemma-The-Writer-9B-abliterated.Q3_K_L.gguf 4.78 GB 8163e289 download
Gemma-The-Writer-9B-abliterated.Q3_K_M.gguf 4.43 GB 9c749db1 download
Gemma-The-Writer-9B-abliterated.Q3_K_S.gguf 4.04 GB b455d1f3 download
Q2_K 1 file 3.54 GB
Gemma-The-Writer-9B-abliterated.Q2_K.gguf 3.54 GB e81ee315 download
Auxiliary files 2 files 6.48 KB
README.md 4.14 KB 9be11313 download
.gitattributes 2.33 KB d006ab82 download

README current version from Hugging Face


base_model: Naphula/Gemma-The-Writer-9B-abliterated
language:

  • en
    library_name: transformers
    license: gemma
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • creative
  • creative writing
  • fiction writing
  • plot generation
  • sub-plot generation
  • fiction writing
  • story generation
  • scene continue
  • storytelling
  • fiction story
  • science fiction
  • romance
  • all genres
  • story
  • writing
  • vivid prosing
  • vivid writing
  • fiction
  • roleplaying
  • bfloat16
  • swearing
  • gemma2
  • rp
  • horror
  • gemma
  • mergekit

About

static quants of https://huggingface.co/Naphula/Gemma-The-Writer-9B-abliterated

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

weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.

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 Q2_K 3.9
GGUF Q3_K_S 4.4
GGUF Q3_K_M 4.9 lower quality
GGUF Q3_K_L 5.2
GGUF Q4_K_S 5.6 fast, recommended
GGUF Q4_K_M 5.9 fast, recommended
GGUF Q5_K_S 6.6
GGUF Q5_K_M 6.7
GGUF Q6_K 7.7 very good quality
GGUF Q8_0 9.9 fast, best quality
GGUF f16 18.6 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. 2025-11-27auto-patch README.mdcd089894.1 KB
    Loading...
  2. 2025-11-24auto-patch README.mdf64cc644 KB
    Loading...
  3. 2025-11-24auto-patch README.mdf317b734 KB
    Loading...
  4. 2025-11-24auto-patch README.md3a4f3103 KB
    Loading...
  5. 2025-11-24uploaded from rich150e0460382 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