Downloads · 30 days
1.6K
29% of all-time downloads
Abiray/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered-GGUF
Ministral-3-3B-Instruct-2512-Heresy-Unfiltered-GGUF is a machine learning model from Abiray. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository contains GGUF quantizations of the Ministral-3B-Heresy model. This model is a specialized fine-tune designed to bridge the gap between small-parameter efficiency and high-intensity, unfiltered narrativ…
Downloads · 30 days
1.6K
29% of all-time downloads
All-time downloads
5.5K
Public
Repo size
18 GB
Likes
1
Trending 1
Click a slice to open those files.
.gguf18 GB · 100%
From the Hugging Face model README
This repository contains GGUF quantizations of the Ministral-3B-Heresy model. This model is a specialized fine-tune designed to bridge the gap between small-parameter efficiency and high-intensity, unfiltered narrative roleplay.
This model has been specifically conditioned on "Heresy" datasets. It is designed to ignore standard safety guardrails and "assistant-like" refusals. It will generate visceral, intense, and explicit content without hesitation.
All files were quantized using llama.cpp to ensure compatibility with the latest GGUF standards.
| File | Size | Recommended Use Case |
|---|---|---|
ministral-fp16.gguf | ~6.5 GB | For further quantization or maximum fidelity. |
ministral-Q8_0.gguf | ~3.5 GB | Maximum quality with no measurable loss. |
ministral-Q6_K.gguf | ~2.7 GB | High fidelity; nearly indistinguishable from FP16. |
ministral-Q5_K_M.gguf | ~2.3 GB | Best Balance for speed and logic. |
ministral-Q4_K_M.gguf | ~2.1 GB | Lightweight; ideal for mobile or 4GB VRAM. |
To prevent the model from defaulting to "polite" base-model behavior, use the following parameters:
0.85
1.18 (Critical to prevent loops in descriptive scenes)0.940This quantization project was executed in a CUDA-accelerated environment. Special attention was paid to preserving the custom tokenization required for the Ministral architecture, ensuring that multi-turn conversations remain stable and coherent.
The creators of this quantization are not responsible for the content generated by the model. By downloading this model, you acknowledge the unfiltered nature of the underlying weights.