Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC
12BMistralheretic
from mistralai/Mistral-Nemo-Instruct-2407
↓ 40K♥ 10122 repos
Mistral-Heretica-12B
Mistral-Heretica-12B is a refusal-ablated variant of MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy, published on Hugging Face by mrcuddle. It is 12B parameters and 24GB VRAM class class. It is distributed across 5 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 7.7K downloads.
Specification
- Model name
- Mistral-Heretica-12B
- Source repository
- mrcuddle/Mistral-Heretica-12B
- Publisher
- mrcuddle
- Parameters
- 12B
- VRAM required
- ~8.1 GB at Q4_K_M, 4k context (estimated) — runs on 12 GB cards
- Hardware class
- 10B – 25B — 24GB VRAM class
- Licence
- Not declared
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 8 Jul 2026
- Last updated
- 22 Sept 2026
Ablation technique
How Mistral-Heretica-12B was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“This is a merge of pre-trained language models created using mergekit.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download AnkitAI/Mistral-Heretica-12B-GGUF --local-dir ./mistral-heretica-12b
llama-cli -m ./mistral-heretica-12b/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "mrcuddle/Mistral-Heretica-12B"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve mrcuddle/Mistral-Heretica-12B --trust-remote-codeDownloads and variants (4)
Every published repository of Mistral-Heretica-12B, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| AnkitAI/Mistral-Heretica-12B-GGUF | GGUF | 5.9K |
| mradermacher/Mistral-Heretica-12B-i1-GGUF | GGUF (imatrix) | 933 |
| mradermacher/Mistral-Heretica-12B-GGUF | GGUF | 596 |
| mrcuddle/Mistral-Heretica-12Bsource | Transformers | 193 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Mistral-Heretica-12B will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- Capability is inherited from MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy, not added by ablation — at 12B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- No licence is declared on this repository, which is a compliance problem in itself. Resolve it against the base model’s terms before use.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for Mistral-Heretica-12B is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with mrcuddle, and does not independently verify publisher claims. See responsible use.