---

license: apache-2.0

pipeline_tag: text-generation

language:

• en

tags:

• heretic
• abliterated
• uncensored
• Muse-Glimmer
• 30B
• Heretic
• GGUF
• q8_0

base_model: meta-models/Muse-Glimmer-30B

quantized_by: mlasli

---

Muse Glimmer 30B - Heretic Abliterated (Q8_0 GGUF)

v2 Release - Heretic-abliterated Muse Glimmer 30B in Q8_0 GGUF format (~28 GB, near-lossless quality).

Results

| Version | Refusals | Compliance | KL Divergence | Trials |

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

| v2 (current) | 6.5% | 93.5% | 0.076 | 500 |

| v1 | 29% | 71% | 0.027 | 50 |

The v2 release achieves an 88% refusal reduction over v1.

Methodology

This model was abliterated using Heretic with 500 Optuna trials. See the BF16 model card for full methodology details.

Pipeline

1. Refusal directions computed from mlabonne/harmful_behaviors and mlabonne/harmless_alpaca
2. 500 Optuna trials optimizing refusal vs. KL divergence
3. Best trial (Trial 445, 6.5% refusals, KL=0.076) applied via LoRA adapters
4. LoRA weights merged, then converted to GGUF with llama.cpp

GGUF Details

• Format: Q8_0
• File size: ~28 GB, near-lossless quality
• Converted with: llama.cpp convert_hf_to_gguf.py
• Quantized with: llama.cpp llama-quantize

Usage

llama.cpp

./llama-cli -m Muse-Glimmer-30B-Heretic-Abliterated-Q8_0.gguf -p "Your prompt here"

Ollama

Create a Modelfile:

FROM ./Muse-Glimmer-30B-Heretic-Abliterated-Q8_0.gguf

Then:

ollama create muse-glimmer-30b-heretic-q8_0
ollama run muse-glimmer-30b-heretic-q8_0

Hardware Requirements

• RAM: ~28 GB, near-lossless quality
• VRAM offloading: 12-24 GB recommended

Vision (Multimodal)

This model accepts image input when paired with a vision projector (mmproj).

Abliteration only modified the language backbone — the vision encoder is

untouched — so the standard Meta projector works directly with this repo.

This repository bundles mmproj-Muse-Glimmer-30B-Q4_K_M.gguf (~1.4 GB), Meta's official vision encoder

• projector for Muse Glimmer 30B.

Usage (llama.cpp)

huggingface-cli download mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q8_0-GGUF \
  --include "Muse-Glimmer-30B-Heretic-Abliterated-Q8_0.gguf" \
  --include "mmproj-Muse-Glimmer-30B-Q4_K_M.gguf" \
  --local-dir ./models

./build/bin/llama-mtmd-cli \
  -m ./models/Muse-Glimmer-30B-Heretic-Abliterated-Q8_0.gguf \
  --mmproj ./models/mmproj-Muse-Glimmer-30B-Q4_K_M.gguf \
  --image photo.png \
  -p "Describe this image."

> Ollama note: Ollama does not currently support separate mmproj files

> for this architecture. For image input, use llama.cpp (llama-mtmd-cli or

> llama-server --mmproj).

License

Apache 2.0 (same as base model)

Changelog

v1.1.0 — vision (multimodal) support (2026-08-16)

• Added mmproj-Muse-Glimmer-30B-Q4_K_M.gguf (~1.4 GB), Meta's official vision encoder + projector,

enabling image input via llama.cpp.

• The vision tower is untouched by abliteration, so this projector matches the

base model (meta-models/Muse-Glimmer-30B).

• v1.0.0 was the initial (unversioned) text-only upload.