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

prithivMLmods/gemma-4-E4B-it-qat-heretic_decensored-GGUF overview

gemma 4 E4B it qat heretic decensored GGUF gemma 4 E4B it qat heretic decensored is a reasoning capable language model built on top of google/gemma 4 E4B it qa…

transformersgguftext-generation-inferencellama-cppdecensoredabliteratedunfilteredunredactedhereticimage-text-to-textenbase_model:prithivMLmods/gemma-4-E4B-it-qat-heretic_decensoredbase_model:quantized:prithivMLmods/gemma-4-E4B-it-qat-heretic_decensoredlicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~533.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
1
Pipeline
image-text-to-text

Repository Files & Downloads

17 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
gemma-4-E4B-it-qat-heretic_decensored.BF16.ggufGGUFGGUF13.92 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.F16.ggufGGUFGGUF13.92 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q2_K.ggufGGUFGGUF4.08 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q3_K_L.ggufGGUFGGUF4.65 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q3_K_M.ggufGGUFGGUF4.49 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q3_K_S.ggufGGUFGGUF4.31 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q4_0.ggufGGUFGGUF4.80 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q4_K_M.ggufGGUFGGUF4.94 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q4_K_S.ggufGGUFGGUF4.82 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q5_0.ggufGGUFGGUF5.26 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q5_K_M.ggufGGUFGGUF5.33 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q5_K_S.ggufGGUFGGUF5.26 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q6_K.ggufGGUFGGUF5.75 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.Q8_0.ggufGGUFGGUF7.40 GBDownload
gemma-4-E4B-it-qat-heretic_decensored.mmproj-bf16.ggufGGUFBF16945.6 MBDownload
gemma-4-E4B-it-qat-heretic_decensored.mmproj-f16.ggufGGUFF16945.6 MBDownload
gemma-4-E4B-it-qat-heretic_decensored.mmproj-q8_0.ggufGGUFQ8_0533.9 MBDownload

Model Details

Model IDprithivMLmods/gemma-4-E4B-it-qat-heretic_decensored-GGUF
AuthorprithivMLmods
Pipelineimage-text-to-text
Licenseapache-2.0
Base modelprithivMLmods/gemma-4-E4B-it-qat-heretic_decensored
Last modified2026-06-18T22:33:28.000Z

Model README

---

base_model:

  • prithivMLmods/gemma-4-E4B-it-qat-heretic_decensored

license: apache-2.0

tags:

  • text-generation-inference
  • llama-cpp
  • decensored
  • abliterated
  • unfiltered
  • unredacted
  • heretic

language:

  • en

pipeline_tag: image-text-to-text

library_name: transformers

---

gemma-4-E4B-it-qat-heretic_decensored-GGUF

> gemma-4-E4B-it-qat-heretic_decensored is a reasoning-capable language model built on top of google/gemma-4-E4B-it-qat-q4_0-unquantized and modified using the Heretic abliteration toolkit. The model applies refusal-direction analysis and targeted weight-space interventions to reduce internal refusal behaviors while preserving instruction-following, reasoning capabilities, and general conversational performance.

> [!IMPORTANT]

> This model is intended strictly for research and learning purposes. Due to reduced internal refusal mechanisms, it may generate sensitive or unrestricted content. Users assume full responsibility for how the model is used. The authors and hosting platform disclaim any liability for generated outputs.

> [!NOTE]

> This model is experimental and may generate unexpected behaviors or artifacts in certain scenarios.

Model Files

File Name | Quant Type | File Size | File Link |

|-----------|------------|-----------|-----------|

| gemma-4-E4B-it-qat-heretic_decensored.BF16.gguf | BF16 | 14.9 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.F16.gguf | F16 | 14.9 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q2_K.gguf | Q2_K | 4.38 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q3_K_L.gguf | Q3_K_L | 4.99 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q3_K_M.gguf | Q3_K_M | 4.82 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q3_K_S.gguf | Q3_K_S | 4.63 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q4_0.gguf | Q4_0 | 5.15 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q4_K_M.gguf | Q4_K_M | 5.3 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q4_K_S.gguf | Q4_K_S | 5.17 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q5_0.gguf | Q5_0 | 5.65 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q5_K_M.gguf | Q5_K_M | 5.72 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q5_K_S.gguf | Q5_K_S | 5.65 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q6_K.gguf | Q6_K | 6.17 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.Q8_0.gguf | Q8_0 | 7.95 GB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.mmproj-bf16.gguf | mmproj-bf16 | 992 MB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.mmproj-f16.gguf | mmproj-f16 | 992 MB | Download |

| gemma-4-E4B-it-qat-heretic_decensored.mmproj-q8_0.gguf | mmproj-q8_0 | 560 MB | Download |

llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp

Run prithivMLmods/gemma-4-E4B-it-qat-heretic_decensored-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