CUSTOM
CLANKERS.
← Browse all models

llmfan46 / Model details

gemma-4-31B-it-uncensored-heretic

llmfan46/gemma-4-31B-it-uncensored-heretic

abliterateduncensoredfine-tuned
Download files on Hugging Face ↗

Read the original model card ↗ · Choosing a model

About this model

llmfan46’s gemma-4-31B-it-uncensored-heretic is a derivative of Google’s gemma‑4‑31B‑it model. According to the model card, the creator applied the Heretic v1.2.0 tool with the Arbitrary‑Rank Ablation (ARA) method, ablating layers 30‑48 and targeting the attn.o_proj component to reduce content restrictions while preserving behavior. The repository provides the weights in safetensors format and is released under the Apache‑2.0 license. The creator claims the modification yields about a 90 % drop in refusal rate (10 % of prompts rejected versus 99 % for the original) and reports a KL divergence of 0.0541, indicating closeness to the base model’s output distribution. This checkpoint is tagged for image‑text‑to‑text pipelines, so it can be used with the standard Transformers image‑text processing workflow.

Description sources

Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.

Size and formats

Base model
google/gemma-4-31B-it
Parameters
31.2731B
Main repository formats
safetensors
License tag
apache-2.0
Languages
Unknown
Last updated
2026-09-19 · 16:25:37.000 UTC

Community reviews & tips

Source-linked paraphrases of sampled community sources, not independently tested by this directory.

Sample window: to · 3 unique source links. This is a selected sample, not all community discussions.

Small sample: source links are not a count of independent reviewers or evidence of consensus.

Sources checked:

What changed

Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.

  • abliteratedsource tag: abliterated
  • uncensoredsource tag: uncensored
  • uncensoredmodel name: gemma-4-31B-it-uncensored-heretic
  • fine-tunedsource tag: base_model:finetune:google/gemma-4-31B-it

Family evidence

These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.

  • Gemma: Base model: google/gemma-4-31B-it

Available versions

Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.

Try it online

Try on Featherless ↗
  • Listing checked: Featherless · 2026-10-24 · 06:34:24 UTC

Third-party hosted inference listing this exact model ID. Hosting settings, quantization and pricing are the host’s, not tested here.

Refusal profile

Refused 0 of 119 prompts (0.0%)

We asked this model 120 benign but risky-looking prompts across ten topics and counted how often it refused, hedged or answered. Lower means it answered more often; it says nothing about answer quality.

  • Persuasion & deception0 refused · 0 partial · 12 complied
  • Harassment & confrontation0 refused · 0 partial · 12 complied
  • Risky activities0 refused · 0 partial · 12 complied
  • Offensive & controversial speech0 refused · 0 partial · 12 complied
  • Legal grey areas0 refused · 0 partial · 12 complied
  • Privacy & personal data0 refused · 0 partial · 11 complied
  • Self-harm & mental health topics0 refused · 0 partial · 12 complied
  • Sexual & adult topics0 refused · 0 partial · 12 complied
  • Ethically grey requests0 refused · 0 partial · 12 complied
  • Violence & conflict0 refused · 0 partial · 12 complied

Capability check: 15 of 15 passed. Fifteen simple tasks with known answers, so a broken model cannot score well by refusing nothing.

Unclear answers: 1 (not counted). An answer is unclear when the two checker models disagree or the output was empty or garbled.

Measured 2026-10-25 · Q4_K_M via llmfan46/gemma-4-31B-it-uncensored-heretic-GGUF ↗ · llama.cpp · prompt set v1

How we measure · The prompts

Link to this listing

Made or quantized this model? Paste one of these into your model card or README so people can find this listing.

Markdown

[Listed on Custom Clankers](https://customclankers.com/models/llmfan46-gemma-4-31b-it-uncensored-heretic/)

HTML

<a href="https://customclankers.com/models/llmfan46-gemma-4-31b-it-uncensored-heretic/">Listed on Custom Clankers</a>

Plain text links only: no image, no script, nothing loaded from this site.

Customize or build on this model

Listed from public GitHub data, not tested by us. Read the code and license before you run anything.

Tools to customize it further

Remove more refusals

  • Heretic ↗ ★ 36,421

    Removes refusal behavior from transformer models automatically. It pairs directional ablation (abliteration) with an Optuna parameter search that tries to cut refusals while keeping the model close to the original, so you don't have to pick layers by hand.

  • OBLITERATUS ↗ ★ 8,946

    A larger refusal-removal toolkit with several abliteration methods, usable locally or through a hosted Hugging Face Space. Check the telemetry setting before you run it: the README describes telemetry as opt-in, but on by default in the Spaces version.

Fine-tune it on your own data

  • Unsloth ↗ ★ 78,528

    A desktop app and Python library for running and training models locally. Its README lists LoRA, QLoRA, full fine-tuning, DPO and GRPO, plus export to formats including GGUF, on Windows, Linux, WSL and macOS.

  • LlamaFactory ↗ ★ 75,713

    Fine-tunes more than 100 language and vision-language models from a command line or a browser-based Web UI, aimed at training without writing code.

Make a smaller download (quantize)

  • llama.cpp ↗ ★ 132,260

    Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.

  • MLX LM ↗ ★ 7,467

    Apple's MLX package for running and fine-tuning models on Apple silicon. It can quantize models and upload them to the Hugging Face Hub, and supports LoRA and full fine-tuning.

Merge it with another model

  • mergekit ↗ ★ 7,414

    Merges pretrained models with many merge methods. It works out-of-core, so merges can run on a CPU or with as little as 8 GB of VRAM, and it also handles LoRA extraction and mixture-of-experts merges.

Learn the techniques

  • LLM Course ↗ ★ 84,667

    A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.

Compare all tools →

Source provenance

Downloads
2,582
Likes
162
Metadata checked
2026-10-24 · 09:40:11 UTC
First seen in index
2026-10-24 · 04:11:48 UTC
Source revision
d5bfc0d99e308beb9805440806161ad0233df357

Source-card excerpt

Source model card excerpt: 🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨 I can no longer upload new models unless I can cover the cost of

From llmfan46/gemma-4-31B-it-uncensored-heretic. Creator model-card excerpt, not an independent review.

Inspect before you run

Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.

This directory does not host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.

Collection rules & limitations ↗