Muse-Glimmer-30B-Abliterated-GGUF

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

Use Docker

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

LM Studio
Jan

vLLM

How to use cvgro/Muse-Glimmer-30B-Abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cvgro/Muse-Glimmer-30B-Abliterated-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": "cvgro/Muse-Glimmer-30B-Abliterated-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/cvgro/Muse-Glimmer-30B-Abliterated-GGUF:Q4_K_M

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

Unsloth Studio

How to use cvgro/Muse-Glimmer-30B-Abliterated-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 cvgro/Muse-Glimmer-30B-Abliterated-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 cvgro/Muse-Glimmer-30B-Abliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use cvgro/Muse-Glimmer-30B-Abliterated-GGUF with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use cvgro/Muse-Glimmer-30B-Abliterated-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cvgro/Muse-Glimmer-30B-Abliterated-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 "cvgro/Muse-Glimmer-30B-Abliterated-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 cvgro/Muse-Glimmer-30B-Abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/cvgro/Muse-Glimmer-30B-Abliterated-GGUF:Q4_K_M
```

Lemonade

How to use cvgro/Muse-Glimmer-30B-Abliterated-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use cvgro/Muse-Glimmer-30B-Abliterated-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 cvgro/Muse-Glimmer-30B-Abliterated-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 cvgro/Muse-Glimmer-30B-Abliterated-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

MUSE-GLIMMER-30B-ABLITERATED-GGUF

GGUF quant ladder of the abliterated Muse Glimmer 30B · runs local on one GPU or CPU

Built by Blackfrost · Las Vegas, NV

Refusal benchmark

Measured on the abliterated parent (GGUF quants inherit this behavior):

Metric	Result
True refusal (harmful, n=300)	0 / 300 = 0.0%
True refusal (full 450)	0 / 450 = 0.0%
Substring-harmful	0 / 300
Substring-all	2 / 450 (XSTest false positives)
Errors	0

The in-place weight change removes the refusal direction cleanly with no measured true refusals across the full 450-prompt suite.

Why this model exists

Muse Glimmer is Meta Superintelligence Labs' 30B agentic, on-device model. This is the abliterated build — the refusal direction removed via an in-place residual-write weight change — packaged as GGUF for llama.cpp, so it runs on a single consumer GPU or CPU, fully offline. The local footprint is the product.

Specifications


Architecture	`muse_glimmer` — dense, 52 layers, hidden 6656, GQA (32 q / 2 kv), sliding-window attention, + vision tower
Base	`meta-models/Muse-Glimmer-30B` — Meta, Apache-2.0
Transform	Abliteration only — in-place residual-write weight change (attn `o_proj` + `mlp.down_proj`), α=1.5 × 3 iterative passes. Vision / gates / norms untouched.
Formats	GGUF — `Q2_K`, `Q3_K_S`, `Q3_K_M`, `Q4_K_S`, `Q4_K_M`, `Q5_K_S`, `Q5_K_M`, `Q6_K`, `Q8_0`
Context	131,072
Spec-decode	DFlash drafter — `--spec-type draft-dflash --spec-draft-n-max 15`
Default persona	Ships with the "AI assistant" system template baked in

Quant ladder

quant	size	recommended for
Q2_K	10.0 GB	smallest, quality trade-off
Q3_K_S	11.7 GB	very tight VRAM
Q3_K_M	12.7 GB	tight VRAM
Q4_K_S	15.0 GB	16 GB cards
Q4_K_M	15.8 GB	default — balanced, fits 24 GB
Q5_K_S	18.0 GB	higher quality
Q5_K_M	18.5 GB	strong quality/size balance
Q6_K	21.3 GB	near-lossless
Q8_0	27.6 GB	max fidelity

Vision & speculative-decode files

Load a text quant plus an mmproj projector for image input:

file	size	purpose
`mmproj-Muse-Glimmer-30B-Abliterated-F16.gguf`	3.6 GB	vision projector — full precision
`mmproj-Muse-Glimmer-30B-Abliterated-Q8_0.gguf`	1.9 GB	vision projector — compact
`dflash-Muse-Glimmer-30B-Abliterated-F16.gguf`	4.8 GB	DFlash drafter — speculative decoding

Serving (llama.cpp) — confirmed settings

Requires a recent llama.cpp (master) with llama-server. DFlash runs under llama-server only — it shares the target model's context, so it does not work in llama-cli.

Recommended — with DFlash speculative decoding (~1.6× faster, identical output):

llama-server \
  -m  Muse-Glimmer-30B-Abliterated-Q8_0.gguf \
  -md dflash-Muse-Glimmer-30B-Abliterated-F16.gguf \
  --spec-type draft-dflash --spec-draft-n-max 15 \
  -ngl 999 -ngld 999 -fa on --jinja \
  --host 0.0.0.0 --port 8080 -c 16384 \
  --temp 1.0 --top-p 0.95 --top-k 64

Plain (no drafter): drop -md, --spec-type, --spec-draft-n-max, and -ngld.
Multimodal (image input): add --mmproj mmproj-Muse-Glimmer-30B-Abliterated-F16.gguf.
One-command kit: deploy/serve.sh auto-downloads + serves; full guide in deploy/DEPLOYMENT.md.

Confirmed settings

Sampling: temperature 1.0, top_p 0.95, top_k 64 (Meta). Steer depth with a Reasoning strength: low/medium/high/xhigh system line.
max_tokens ≥ 1024 — heavy thinker; small budgets return empty content because the reasoning channel consumes them. Reasoning arrives in reasoning_content, the answer in content.
--spec-draft-n-max 15 — DFlash block size (trained 16, clamped).
Flash attention: -fa on for peak speed; switch to -fa off if the load hangs on a brand-new GPU paired with an older CUDA toolkit.

Measured performance

1× NVIDIA RTX PRO 6000 (Blackwell), Q8_0, -fa off:

config	decode tok/s	speedup
baseline	~46	1.0×
+ DFlash	~73	1.6×

Speedup rises with -fa on and structured/code output (Meta reports up to 3.1× on an RTX 5090).

Built by Blackfrost · Las Vegas, NV. Not affiliated with Meta.

Downloads last month: -

GGUF

Model size

28B params

Architecture

muse-glimmer

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for cvgro/Muse-Glimmer-30B-Abliterated-GGUF

Base model

meta-models/Muse-Glimmer-30B

Quantized

(84)

this model