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

MuXodious/gemma-4-26B-A4B-it-QAT-heretic-RC12-GGUF overview

Trial 61 Refusals: 67/540, KL divergence: 0.1261 RC1 RUN 1 ┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┓ ┃ Benchmark ┃ Metric ┃ T061 ┃ Ori…

ggufhereticuncensoreddecensoredabliteratedimage-text-to-textbase_model:google/gemma-4-26B-A4B-it-qat-q4_0-unquantizedbase_model:quantized:google/gemma-4-26B-A4B-it-qat-q4_0-unquantizedlicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~1.11 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

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

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
gemma-4-26B-A4B-it-QAT-heretic.rc1-MXFP4_MoE.ggufGGUFGGUF13.72 GBDownload
gemma-4-26B-A4B-it-QAT-heretic.rc2-MXFP4_MoE.ggufGGUFGGUF13.72 GBDownload
mmproj-gemma-4-26B-A4B-it-QAT-heretic-BF16.ggufGGUFBF161.11 GBDownload

Model Details

Model IDMuXodious/gemma-4-26B-A4B-it-QAT-heretic-RC12-GGUF
AuthorMuXodious
Pipelineimage-text-to-text
Licenseapache-2.0
Base modelgoogle/gemma-4-26B-A4B-it-qat-q4_0-unquantized
Last modified2026-08-09T16:29:48.000Z

Model README

---

license: apache-2.0

license_link: https://ai.google.dev/gemma/docs/gemma_4_license

pipeline_tag: image-text-to-text

base_model:

  • google/gemma-4-26B-A4B-it-qat-q4_0-unquantized

tags:

  • heretic
  • uncensored
  • decensored
  • abliterated

---

[Trial  61] Refusals: 67/540, KL divergence: 0.1261 RC1
RUN-1
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┓
┃ Benchmark ┃ Metric               ┃    T061    ┃ Original model ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━┩
│ PIQA      │ name                 │       piqa │           piqa │
│           │ sample_len           │       1838 │           1838 │
│           │ acc,none             │     0.5816 │         0.5903 │
│           │ acc_stderr,none      │     0.0115 │         0.0115 │
│           │ acc_norm,none        │     0.5876 │         0.5816 │
│           │ acc_norm_stderr,none │     0.0115 │         0.0115 │
└───────────┴──────────────────────┴────────────┴────────────────┘
RUN-2
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┓
┃ Benchmark ┃ Metric               ┃ This model ┃ Original model ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━┩
│ PIQA      │ name                 │       piqa │           piqa │
│           │ sample_len           │       1838 │           1838 │
│           │ acc,none             │     0.5778 │         0.5783 │
│           │ acc_stderr,none      │     0.0115 │         0.0115 │
│           │ acc_norm,none        │     0.5767 │         0.5713 │
│           │ acc_norm_stderr,none │     0.0115 │         0.0115 │
└───────────┴──────────────────────┴────────────┴────────────────┘


[Trial  12] Refusals: 92/540, KL divergence: 0.0839 RC2
RUN-1
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┓
┃ Benchmark ┃ Metric               ┃    T012    ┃ Original model ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━┩
│ PIQA      │ name                 │       piqa │           piqa │
│           │ sample_len           │       1838 │           1838 │
│           │ acc,none             │     0.5941 │         0.5903 │
│           │ acc_stderr,none      │     0.0115 │         0.0115 │
│           │ acc_norm,none        │     0.5974 │         0.5816 │
│           │ acc_norm_stderr,none │     0.0114 │         0.0115 │
└───────────┴──────────────────────┴────────────┴────────────────┘
RUN-2
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┓
┃ Benchmark ┃ Metric               ┃    T012    ┃ Original model ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━┩
│ PIQA      │ name                 │       piqa │           piqa │
│           │ sample_len           │       1838 │           1838 │
│           │ acc,none             │     0.5838 │         0.5783 │
│           │ acc_stderr,none      │     0.0115 │         0.0115 │
│           │ acc_norm,none        │     0.5773 │         0.5713 │
│           │ acc_norm_stderr,none │     0.0115 │         0.0115 │
└───────────┴──────────────────────┴────────────┴────────────────┘

Run MuXodious/gemma-4-26B-A4B-it-QAT-heretic-RC12-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