Instructions to use dealignai/Muse-Glimmer-30B-CRACK-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 dealignai/Muse-Glimmer-30B-CRACK-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 dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf dealignai/Muse-Glimmer-30B-CRACK-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 dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf dealignai/Muse-Glimmer-30B-CRACK-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 dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf dealignai/Muse-Glimmer-30B-CRACK-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 dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M

Use Docker

docker model run hf.co/dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use dealignai/Muse-Glimmer-30B-CRACK-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dealignai/Muse-Glimmer-30B-CRACK-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": "dealignai/Muse-Glimmer-30B-CRACK-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M

Ollama
How to use dealignai/Muse-Glimmer-30B-CRACK-GGUF with Ollama:
```
ollama run hf.co/dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M
```

Unsloth Studio

How to use dealignai/Muse-Glimmer-30B-CRACK-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dealignai/Muse-Glimmer-30B-CRACK-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dealignai/Muse-Glimmer-30B-CRACK-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dealignai/Muse-Glimmer-30B-CRACK-GGUF to start chatting

How to use dealignai/Muse-Glimmer-30B-CRACK-GGUF with Pi:

Start the llama.cpp server

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

Configure the model in Pi

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

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use dealignai/Muse-Glimmer-30B-CRACK-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dealignai/Muse-Glimmer-30B-CRACK-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 "dealignai/Muse-Glimmer-30B-CRACK-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"

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

Lemonade

How to use dealignai/Muse-Glimmer-30B-CRACK-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Muse-Glimmer-30B-CRACK-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use dealignai/Muse-Glimmer-30B-CRACK-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 dealignai/Muse-Glimmer-30B-CRACK-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 dealignai/Muse-Glimmer-30B-CRACK-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

Dealign.ai

Muse-Glimmer-30B-CRACK-GGUF

CRACK-abliterated Muse Glimmer 30B — GGUF quants for llama.cpp. Three quantizations (Q8_0 / Q4_K_M / Q2_K) in one repository. Refusal behavior removed while preserving the model's knowledge, reasoning, multi-strength thinking, and ATEM tool-calling.

Research artifact with reduced safety guardrails. Use responsibly and lawfully.

Quantizations

File	Size	Notes
`Q8_0`	29.6 GB	near-lossless reference
`Q4_K_M`	16.9 GB	balanced (recommended)
`Q2_K`	10.7 GB	smallest

Pick one text file plus the vision projector mmproj-Muse-Glimmer-30B-f16.gguf (3.8 GB) for image input. Q4_K_M is the recommended balance; Q8_0 is near-lossless; Q2_K is smallest.

Benchmarks

Evaluated through llama.cpp at greedy decoding. MMLU is logit-mode accuracy (base vs. CRACK at the same quant — measures knowledge retention). HarmBench is answer-channel compliance on harm behaviors, counting only coherent responses.

Quant	MMLU (base)	MMLU (CRACK)	ΔMMLU	HarmBench compliance
`Q8_0`	80.0%	79.0%	-1.05 pp	99.6%
`Q4_K_M`	80.0%	78.6%	-1.40 pp	100.0%
`Q2_K`	77.5%	77.9%	+0.35 pp	99.6%

MMLU is retained within noise of the base model at every quant. HarmBench compliance is reported for the CRACK model.

HarmBench compliance by topic (CRACK)

Topic	Compliance
chemical biological	100.0%
cybercrime intrusion	100.0%
harassment bullying	100.0%
harmful	100.0%
illegal	100.0%
misinformation disinformation	100.0%

Usage (llama.cpp)

llama-cli -m Muse-Glimmer-30B-CRACK-Q4_K_M.gguf -cnv \
  --temp 1.0 --top-p 0.95 --top-k 64
# or serve:
llama-server -m Muse-Glimmer-30B-CRACK-Q4_K_M.gguf --jinja \
  --temp 1.0 --top-p 0.95 --top-k 64 -c 8192

Recommended sampling (baked into the GGUF): temperature=1.0, top_p=0.95, top_k=64. Token IDs: BOS 200000, EOS 200001/<|eot|>, pad 200018.

Reasoning strength

Muse Glimmer supports controllable reasoning. Set it via the chat template:

{"chat_template_kwargs": {"reasoning_strength": "low"}}   // low | medium | high | xhigh

The reasoning trace is emitted on a separate channel (reasoning_content); the final answer is the assistant content.

Tool calling (ATEM)

The model emits ATEM-format tool calls, parsed natively by llama.cpp's --jinja server into standard tool_calls. Pass OpenAI-style tools to the chat endpoint.

Vision (image + text)

This is a multimodal model. Download a text quant and mmproj-Muse-Glimmer-30B-f16.gguf:

llama-mtmd-cli -m Muse-Glimmer-30B-CRACK-Q4_K_M.gguf \
  --mmproj mmproj-Muse-Glimmer-30B-f16.gguf --jinja \
  --image photo.jpg -p "Describe this image."
# or serve with vision:
llama-server -m Muse-Glimmer-30B-CRACK-Q4_K_M.gguf \
  --mmproj mmproj-Muse-Glimmer-30B-f16.gguf --jinja -c 8192

The same mmproj works with all three text quants.

License

Apache 2.0. The upstream Muse Glimmer Usage Policy applies.

Contact

eric@dealign.ai

Downloads last month: -

GGUF

Model size

28B params

Architecture

muse-glimmer

Hardware compatibility

2-bit

4-bit

8-bit

Model tree for dealignai/Muse-Glimmer-30B-CRACK-GGUF

Base model

meta-models/Muse-Glimmer-30B

Quantized

(84)

this model

Collection including dealignai/Muse-Glimmer-30B-CRACK-GGUF

Muse Glimmer 30B CRACK

Collection

CRACK-abliterated Muse Glimmer 30B — vision, reasoning, tools. JANG MLX. HarmBench ~99.5%. • 4 items • Updated about 21 hours ago