GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

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

Gemma 4 12b it Abliterated — GGUF quant ladder Quantized GGUF builds of Carlosian/Gemma 4 12b it Abliterated https://huggingface.co/Carlosian/Gemma 4 12b it Ab…

ggufquantizedabliterateduncensoredllama.cpptext-generationarxiv:2605.12290base_model:Carlosian/Gemma-4-12b-it-Abliteratedbase_model:quantized:Carlosian/Gemma-4-12b-it-Abliteratedlicense:otherendpoints_compatibleregion:usconversational

Runs locally from ~4.50 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

11 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Gemma-4-12b-it-Abliterated.Q2_K.ggufGGUFGGUF4.50 GBDownload
Gemma-4-12b-it-Abliterated.Q3_K_M.ggufGGUFGGUF5.67 GBDownload
Gemma-4-12b-it-Abliterated.Q3_K_S.ggufGGUFGGUF5.15 GBDownload
Gemma-4-12b-it-Abliterated.Q4_0.ggufGGUFGGUF6.50 GBDownload
Gemma-4-12b-it-Abliterated.Q4_K_M.ggufGGUFGGUF6.87 GBDownload
Gemma-4-12b-it-Abliterated.Q4_K_S.ggufGGUFGGUF6.54 GBDownload
Gemma-4-12b-it-Abliterated.Q5_K_M.ggufGGUFGGUF7.96 GBDownload
Gemma-4-12b-it-Abliterated.Q5_K_S.ggufGGUFGGUF7.77 GBDownload
Gemma-4-12b-it-Abliterated.Q6_K.ggufGGUFGGUF9.11 GBDownload
Gemma-4-12b-it-Abliterated.Q8_0.ggufGGUFGGUF11.80 GBDownload
Gemma-4-12b-it-Abliterated.f16.ggufGGUFGGUF22.20 GBDownload

Model Details

Model IDCarlosian/Gemma-4-12b-it-Abliterated-GGUF
AuthorCarlosian
Pipelinetext-generation
Licenseother
Base modelCarlosian/Gemma-4-12b-it-Abliterated
Last modified2026-07-20T05:57:32.000Z

Model README

---

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.

Run Carlosian/Gemma-4-12b-it-Abliterated-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models