---

base_model: coder3101/Anubis-Mini-8B-v1-heretic

base_model_relation: quantized

library_name: gguf

license: apache-2.0

language:

• en

pipeline_tag: text-generation

tags:

• gguf
• text-generation
• roleplay
• creative-writing
• chat
• abliterated
• uncensored
• llama-3.3
• q4_k_m
• iq4_nl
• imatrix
• conversational

---

Anubis-Mini-8B-v1-heretic — Importance Matrix GGUF

This repository hosts importance-matrix (imatrix) optimized GGUF weights, available in multiple quantization formats, for Anubis-Mini-8B-v1-heretic, quantized from the source floating-point tensors provided by coder3101/Anubis-Mini-8B-v1-heretic.

About the Model

Anubis-Mini-8B-v1 is a Llama-3.3-8B fine-tune by TheDrummer, purpose-built for immersive roleplay, collaborative storytelling, and creative writing. TheDrummer's models prioritise creativity, dynamism, imagination, and reduced alignment over benchmark scores — the goal is to broaden the model's range of expression for fiction, TTRPG, and entertainment use cases rather than optimise for factual correctness or safety compliance.

The heretic suffix denotes post-processing via the Heretic v1.3.0 abliteration framework performed by coder3101, which surgically suppresses refusal vectors while preserving the model's core creative and roleplay capabilities.

---

Model & Architecture Specifications

| Property | Value |

|---|---|

| Base Architecture | Llama-3.3-8B dense transformer |

| Fine-tuned by | TheDrummer |

| Primary Use | Roleplay, creative writing, storytelling |

| Context Window | 131,072 tokens |

| Abliteration Tool | Heretic v1.3.0 |

| Abliteration Method | direction_index (single-direction refusal suppression) |

| Prompt Format | Llama 3 Chat Template |

---

Abliteration Parameters

| Parameter | Value |

|---|---|

| direction_index | 18.95 |

| attn.o_proj.max_weight | 1.49 |

| attn.o_proj.max_weight_position | 25.33 |

| attn.o_proj.min_weight | 1.22 |

| attn.o_proj.min_weight_distance | 15.18 |

| mlp.down_proj.max_weight | 0.91 |

| mlp.down_proj.max_weight_position | 22.67 |

| mlp.down_proj.min_weight | 0.67 |

| mlp.down_proj.min_weight_distance | 8.69 |

Abliteration Performance

> [!NOTE]

> The metrics below are self-reported by the original model author (coder3101) and have not been independently reproduced.

| Metric | This model | Original (TheDrummer/Anubis-Mini-8B-v1) |

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

| KL divergence | 0.0082 | 0 (by definition) |

| Refusals | 6/100 | 84/100 |

---

Quantization Details

| Property | Value |

|---|---|

| Quantization Types | Q4_K_M, IQ4_NL (both with imatrix calibration) |

| Importance Matrix | bartowski's calibration_datav5.txt |

Quantization Commands

# Q4_K_M
./llama-quantize --imatrix /content/imatrix.dat \
  /content/model-bf16.gguf \
  /content/Anubis-Mini-8B-v1-heretic-Q4_K_M-imatrix.gguf q4_k_m

# IQ4_NL
./llama-quantize --imatrix /content/imatrix.dat \
  /content/model-bf16.gguf \
  /content/Anubis-Mini-8B-v1-heretic-IQ4_NL-imatrix.gguf iq4_nl

---

Repository Files

| Filename | Format | Size | llama.cpp Build | Description |

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

| Anubis-Mini-8B-v1-heretic-Q4_K_M-imatrix.gguf | Q4_K_M | 4.92 GB | b9803 | Main model weights, imatrix-calibrated |

| Anubis-Mini-8B-v1-heretic-IQ4_NL-imatrix.gguf | IQ4_NL | 4.68 GB | b9837 | Main model weights, imatrix-calibrated, smaller non-linear 4-bit quant |

---

Inference

> [!TIP]

> Swap the -m filename below for either quantized file depending on your size/quality trade-off preference.

llama.cpp CLI

./llama-cli \
  -m Anubis-Mini-8B-v1-heretic-Q4_K_M-imatrix.gguf \
  -c 8192 \
  -ngl 99 \
  -p "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\nYou are a skilled storyteller and collaborative roleplay partner.<|eot_id|>\n<|start_header_id|>user<|end_header_id|>\nLet's begin a fantasy adventure. You play the mysterious innkeeper.<|eot_id|>\n<|start_header_id|>assistant<|end_header_id|>\n"

OpenAI-Compatible API Server

./llama-server \
  --host 0.0.0.0 \
  --port 8080 \
  -m Anubis-Mini-8B-v1-heretic-Q4_K_M-imatrix.gguf \
  -c 16384 \
  -ngl 99 \
  --flash-attn

---

Prompt Format (Llama 3 Chat Template)

<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a vivid and immersive creative writing partner.<|eot_id|>
<|start_header_id|>user<|end_header_id|>
Your prompt here.<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>

---

Notes & Limitations

• This model is abliterated and will generate content that standard aligned models refuse. Use responsibly and in compliance with applicable laws.
• Optimised for creative and roleplay tasks; not specifically tuned for factual Q&A, coding, or tool use.
• Imatrix calibration improves perplexity recovery compared to non-imatrix quantization, particularly on low-frequency tokens critical to narrative writing.
• IQ4_NL produces a smaller file than Q4_K_M and tends to run faster on CPU and ARM devices; imatrix calibration narrows the quality gap between the two formats considerably.