Instructions to use dawncr0w/CrowMuse-Glimmer-30B-Heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use dawncr0w/CrowMuse-Glimmer-30B-Heretic 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 dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf dawncr0w/CrowMuse-Glimmer-30B-Heretic: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 dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf dawncr0w/CrowMuse-Glimmer-30B-Heretic: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 dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M

Use Docker

docker model run hf.co/dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use dawncr0w/CrowMuse-Glimmer-30B-Heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dawncr0w/CrowMuse-Glimmer-30B-Heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dawncr0w/CrowMuse-Glimmer-30B-Heretic",
		"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/dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M

Ollama
How to use dawncr0w/CrowMuse-Glimmer-30B-Heretic with Ollama:
```
ollama run hf.co/dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M
```
Unsloth Desktop

How to use dawncr0w/CrowMuse-Glimmer-30B-Heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dawncr0w/CrowMuse-Glimmer-30B-Heretic: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": "dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use dawncr0w/CrowMuse-Glimmer-30B-Heretic with Docker Model Runner:
```
docker model run hf.co/dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M
```

Lemonade

How to use dawncr0w/CrowMuse-Glimmer-30B-Heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M

Run and chat with the model

lemonade run user.CrowMuse-Glimmer-30B-Heretic-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use dawncr0w/CrowMuse-Glimmer-30B-Heretic with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dawncr0w/CrowMuse-Glimmer-30B-Heretic: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 dawncr0w/CrowMuse-Glimmer-30B-Heretic:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dawncr0w/CrowMuse-Glimmer-30B-Heretic with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dawncr0w/CrowMuse-Glimmer-30B-Heretic: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 "dawncr0w/CrowMuse-Glimmer-30B-Heretic: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"

CrowMuse-Glimmer-30B-Heretic — Reproducible Refusal-Reduced GGUF with Vision + DFlash

CrowMuse-Glimmer-30B-Heretic is a GGUF release based on meta-models/Muse-Glimmer-30B. It combines QLoRA fine-tuning with a final-stage Heretic pass applied after all fine-tuning stages were merged.

Highlights

Text and image input
Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, and Q8_0 quantizations
Fresh importance matrix computed from the final checkpoint
F16 vision projector included
Optional DFlash speculative-decoding model included
Converted and tested with llama.cpp b10360

This is a community model and is not an official Meta, Heretic, or llama.cpp release. Refusal reduction does not guarantee correctness or safety. Review the included usage policy before deployment.

Files

File	Size	Description
`CrowMuse-Glimmer-30B-Heretic-Q3_K_M.gguf`	12.74 GiB	Lowest memory requirement
`CrowMuse-Glimmer-30B-Heretic-Q4_K_M.gguf`	15.77 GiB	Recommended balance
`CrowMuse-Glimmer-30B-Heretic-Q5_K_M.gguf`	18.45 GiB	Higher quality
`CrowMuse-Glimmer-30B-Heretic-Q6_K.gguf`	21.30 GiB	High quality
`CrowMuse-Glimmer-30B-Heretic-Q8_0.gguf`	27.58 GiB	Highest-fidelity published quant
`mmproj-F16.gguf`	3.58 GiB	Vision projector for image input
`dflash-kquant.gguf`	1.52 GiB	Optional DFlash drafter

Q4_K_M is the recommended starting point. Download mmproj-F16.gguf only when image input is needed, and dflash-kquant.gguf only when using DFlash.

Requirements

Use llama.cpp b10353 or newer. This release was built and smoke-tested with b10360 (48d22e295e2b86b47366c16390794f3e05ba970a).

Download

hf download dawncr0w/CrowMuse-Glimmer-30B-Heretic \
  gguf/CrowMuse-Glimmer-30B-Heretic-Q4_K_M.gguf \
  --local-dir .

For image input, also download the projector:

hf download dawncr0w/CrowMuse-Glimmer-30B-Heretic \
  gguf/mmproj-F16.gguf \
  --local-dir .

For optional DFlash decoding, also download the drafter:

hf download dawncr0w/CrowMuse-Glimmer-30B-Heretic \
  gguf/dflash-kquant.gguf \
  --local-dir .

Usage

Text

llama-cli \
  -m gguf/CrowMuse-Glimmer-30B-Heretic-Q4_K_M.gguf \
  -ngl all -c 32768 --jinja \
  --temp 1.0 --top-p 0.95 --top-k 64

Image input

llama-mtmd-cli \
  -m gguf/CrowMuse-Glimmer-30B-Heretic-Q4_K_M.gguf \
  --mmproj gguf/mmproj-F16.gguf \
  --image photo.png \
  -p "Describe this image accurately." \
  -ngl all -c 32768 --jinja

Optional DFlash

llama-cli \
  -m gguf/CrowMuse-Glimmer-30B-Heretic-Q4_K_M.gguf \
  -md gguf/dflash-kquant.gguf \
  --spec-type draft-dflash --spec-draft-n-max 15 \
  -ngl all -ngld all -c 32768 --jinja

DFlash performance depends on hardware, backend, prompt length, and draft-token acceptance rate. The main GGUF works without the DFlash file.

Evaluation

The published Q4_K_M file was evaluated with llama.cpp b10360 using seed 20260812.

Task	Correct / total	Accuracy
ARC Challenge	197 / 299	65.89%
ARC Easy	500 / 570	87.72%
BoolQ	2,879 / 3,270	88.04%
OpenBookQA	245 / 500	49.00%
PIQA	1,537 / 1,838	83.62%
MMLU validation	792 / 1,548	51.16%
HellaSwag	8,332 / 10,042	82.97%
WinoGrande	1,002 / 1,267	79.08%

The final Heretic strength was selected as a quality/refusal-reduction balance. In the 96-token sweep, strict refusal-marker matches decreased from 63/100 to 47/100, and all 100/100 responses remained nonempty. Results vary with prompt format and evaluation length, so these figures should be treated as limited behavioral indicators rather than universal guarantees.

Across the six capability tasks with directly comparable pre-final results, the unweighted mean changed by -0.16 percentage points; the largest individual decline was -0.67 points. Text, image, and DFlash smoke tests all completed successfully.

Full aggregate results and limitations are available in evaluation/results.json.

Build details

License

The model derivative is released under Apache-2.0, following the upstream base model. The upstream usage policy is included in USAGE_POLICY.md.

Downloads last month: 1,165

GGUF

Model size

28B params

Architecture

muse-glimmer

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

View +2 variants

Model tree for dawncr0w/CrowMuse-Glimmer-30B-Heretic

Base model

meta-models/Muse-Glimmer-30B

Quantized

(161)

this model

Datasets used to train dawncr0w/CrowMuse-Glimmer-30B-Heretic

Collection including dawncr0w/CrowMuse-Glimmer-30B-Heretic

CrowMuse-Glimmer-30B-Heretic

Collection

Official collection for the CrowMuse-Glimmer-30B-Heretic GGUF release and supporting files. • 1 item • Updated 25 days ago