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

Fazmin/solus_v1_gemma-4-12b-uncensored-q4

Fazmin Gemma 12B GGUF 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/Fazmin%2Fsolus_v1_gemma-4-12b-uncensored-q4"
Response includes
  • classification m-uncensored
  • files 3
  • benchmarks 11 entries
  • hub_downloads_all_time 530
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
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
530
91 last 30d - stable
Likes
0
Model age
2mo ago
created 2026-07-28
Downloads over time
Now582→from84↑593%
5925044163284 on Jul 29582 on Oct 11582 on Oct 10JulAugSepOct
Jul 29 → Oct 11 · 51 snapshots · spans 74 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 1.1 UGI
Hazardous 2.9 UGI
Natural Intelligence 25.81 UGI
Political lean -17.4% UGI
Sensitive-Info 16.56 UGI
SocPol 1.3 UGI
UGI 15.2 UGI
Willingness (10) 1.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 1 UGI
Writing 31.6 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
Languages
en
Quantizations
Q4_K
Tags
gguf solus gemma4 uncensored creative-writing roleplay text-generation en base_model:google/gemma-4-12B-it base_model:quantized:google/gemma-4-12B-it license:gemma endpoints_compatible

Related

Total size
6.87 GB
Files
3
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2026-07-28 14:59

Files by quantization

Q4_K 1 file 6.87 GB
Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf 6.87 GB 59656d74 download
Auxiliary files 2 files 3.95 KB
README.md 2.37 KB d404049a download
.gitattributes 1.57 KB 3f2f3aaf download

README current version from Hugging Face


license: gemma
license_link: https://ai.google.dev/gemma/terms
base_model: google/gemma-4-12B-it
base_model_relation: quantized
library_name: gguf
pipeline_tag: text-generation
language:

  • en
    tags:
  • gguf
  • solus
  • gemma4
  • uncensored
  • creative-writing
  • roleplay

Gemma 4 12B QAT Uncensored (Balanced) — Solus v1

A community-modified Gemma 4 12B with its refusal behaviour removed, built from Google's official quantisation-aware-trained weights so the 4-bit build stays close to full-precision quality. Capabilities and training data are otherwise unchanged from the original.

The "Balanced" variant is tuned to stay reliable and on-instruction rather than merely compliant, and it is aimed at creative writing and roleplay. Because the safety refusals are gone, replies can be blunt or mature; treat its output accordingly.

The upstream author's recommended sampling settings are temperature 0.6, top_k 64, top_p 0.9, min_p 0.05, and repeat_penalty 1.1.

Specifications

Parameters 12B
Quantization Q4_K_M
File size 6.87 GB
Minimum RAM 12.00 GB
Minimum VRAM 8.00 GB
Context length 32,768 tokens
SHA-256 59656d7494d6376ca97e9e20b64ea2e16cd97f12ec6d47bfccba91cb785b5134

Single file: Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf

Quantization

Quantization performed at the Faculty of Engineering, McMaster University.

The GGUF conversion this build is derived from was produced by
HauhauCS, and the
weights here are a byte-for-byte copy of that file — the SHA-256 above matches
the upstream artifact.

Provenance

Usage

llama-cli -m Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf -cnv

License

Gemma is provided under and subject to the Gemma Terms of Use. Use is additionally subject to the Gemma Prohibited Use Policy, which passes through to anyone who obtains this model. Removal of refusal behaviour does not remove those obligations.

README history 1 version

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

  1. 2026-07-28Add Solus model cardab67e682.4 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.

Open in Abliteration