Instructions to use mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Ollama
How to use mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M
```
Unsloth Desktop

How to use mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Muse Glimmer 30B - Heretic Abliterated (Q4_K_M GGUF)

v2 Release - Heretic-abliterated Muse Glimmer 30B in Q4_K_M GGUF format (~16 GB, good quality/size balance).

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

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

GGUF Details

Format: Q4_K_M
File size: ~16 GB, good quality/size balance
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-Q4_K_M.gguf -p "Your prompt here"

Ollama

Create a Modelfile:

FROM ./Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M.gguf

Then:

ollama create muse-glimmer-30b-heretic-q4_k_m
ollama run muse-glimmer-30b-heretic-q4_k_m

Hardware Requirements

RAM: ~16 GB, good quality/size balance
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-Q4_K_M-GGUF \
  --include "Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M.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-Q4_K_M.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.

Downloads last month: 990

GGUF

Model size

28B params

Architecture

muse-glimmer

Hardware compatibility

4-bit

Model tree for mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF

Base model

meta-models/Muse-Glimmer-30B

Quantized

(163)

this model

Collection including mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF

Muse Glimmer Heretic Abliterated

Collection

Collection of my Heretic Abliterated Muse Models • 4 items • Updated 22 days ago