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

Carlosian/Gemma-4-12b-it-Abliterated-GGUF

Carlosian Gemma 12B GGUF second-order 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/Carlosian%2FGemma-4-12b-it-Abliterated-GGUF"
Response includes
  • classification m8
  • files 16
  • hub_downloads_all_time 805
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=Carlosian
All 4 models by Carlosian
 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
805
303 last 30d - stable
Likes
0
Model age
3mo ago
created 2026-06-29
Downloads over time
Now889→from242↑267%
210458706954242 on Jul 22889 on Oct 12JulAugSepOct
Jul 22 → Oct 12 · 53 snapshots · spans 82 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.

Carlosian/Gemma-4-12b-it-Abliterated↓ 30 this lineage
Carlosian/Gemma-4-12b-it-Abliterated-GGUF↓ 303

Variants by this author 2 formats · 333 downloads combined

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

Metadata

License
other
Quantizations
F16 Q2_K Q3_K Q4 Q4_K Q5_K Q6_K Q8_0
Tags
gguf quantized abliterated uncensored llama.cpp text-generation arxiv:2605.12290 base_model:Carlosian/Gemma-4-12b-it-Abliterated base_model:quantized:Carlosian/Gemma-4-12b-it-Abliterated license:other endpoints_compatible region:us

Related

Other by Carlosian
Qwen3.5-35B-A3B-Abliterated 11K Qwen3.5-35B-A3B-Abliterated-GGUF 763 Gemma-4-12b-it-Abliterated 30
Same base model
mradermacher/Gemma-4-12b-it-Abliterated-i1-GGUF 2K mradermacher/Gemma-4-12b-it-Abliterated-GGUF 1K
Total size
94.1 GB
Files
16
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2026-07-20 05:57
Source huggingface.co/Carlosian/Gemma-4-12b-it-Abliterated-GGUF ↗ Base model Carlosian/Gemma-4-12b-it-Abliterated →

Files by quantization

F16 1 file 22.2 GB
Gemma-4-12b-it-Abliterated.f16.gguf 22.2 GB 15356b97 download
Q8_0 1 file 11.8 GB
Gemma-4-12b-it-Abliterated.Q8_0.gguf 11.8 GB 38e197b5 download
Q6_K 1 file 9.11 GB
Gemma-4-12b-it-Abliterated.Q6_K.gguf 9.11 GB dd188a28 download
Q5_K 2 files 15.7 GB
Gemma-4-12b-it-Abliterated.Q5_K_M.gguf 7.96 GB 3b1295df download
Gemma-4-12b-it-Abliterated.Q5_K_S.gguf 7.77 GB 2cae74b3 download
Q4_K 2 files 13.4 GB
Gemma-4-12b-it-Abliterated.Q4_K_M.gguf 6.87 GB 279adedd download
Gemma-4-12b-it-Abliterated.Q4_K_S.gguf 6.54 GB 79e9eefb download
Q4 1 file 6.50 GB
Gemma-4-12b-it-Abliterated.Q4_0.gguf 6.50 GB 12a5a4a8 download
Q3_K 2 files 10.8 GB
Gemma-4-12b-it-Abliterated.Q3_K_M.gguf 5.67 GB 78fde8c5 download
Gemma-4-12b-it-Abliterated.Q3_K_S.gguf 5.15 GB 11e173aa download
Q2_K 1 file 4.50 GB
Gemma-4-12b-it-Abliterated.Q2_K.gguf 4.50 GB 77e66dd8 download
Auxiliary files 5 files 72.0 KB
convert.log 67.4 KB 02accfe7 download
.gitattributes 2.28 KB 2e522e62 download
README.md 1.24 KB 328df9fb download
manifest.jsonl 1.11 KB 0f52fc4b download
smoke.txt 11.0 B 67e65c47 download

README current version from Hugging Face

base_model: Carlosian/Gemma-4-12b-it-Abliterated
base_model_relation: quantized
library_name: gguf
pipeline_tag: text-generation
tags:

  • gguf
  • quantized
  • abliterated
  • uncensored
  • llama.cpp
    license: other

Gemma-4-12b-it-Abliterated — GGUF quant ladder

Quantized GGUF builds of Carlosian/Gemma-4-12b-it-Abliterated for llama.cpp / Ollama / LM Studio.

Quant Typical use
Q2_K smallest / extreme low VRAM
Q3_K_S / Q3_K_M low VRAM
Q4_0 / Q4_K_S / Q4_K_M recommended default (Q4_K_M)
Q5_K_S / Q5_K_M higher quality
Q6_K near-lossless
Q8_0 highest quality quant
F16 full intermediate (large)

Built with llama.cpp on Thunder Compute (A100). Generated 2026-07-20.

Acknowledgments & method references

The refusal-removal method used to build the base checkpoint draws on:

  • Herring, S., Naviasky, J., Malhotra, K. (2026). Targeted Neuron Modulation via Contrastive Pair Search. Nous Research. https://huggingface.co/papers/2605.12290
  • Nous Research (2026). llm-abliteration — toolkit for abliteration (norm-preserving & biprojected variants, multi-architecture). github.com/NousResearch/llm-abliteration.

README history 3 versions

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

  1. 2026-07-20Add acknowledgments/citations for Nous Research CNA paper + llm-abliteration ...19b761b1.2 KB
    Loading...
  2. 2026-07-20Add full GGUF quant ladder for Gemma-4-12b-it-Abliterated45ade00815 B
    Loading...
  3. 2026-06-29Add model cardbd830cc3.1 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