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

Use Docker

docker model run hf.co/NANI-Nithin/Muse-Glimmer-30B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use NANI-Nithin/Muse-Glimmer-30B-GGUF with vLLM:

Install from pip and serve model

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

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

Unsloth Studio

How to use NANI-Nithin/Muse-Glimmer-30B-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 NANI-Nithin/Muse-Glimmer-30B-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 NANI-Nithin/Muse-Glimmer-30B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use NANI-Nithin/Muse-Glimmer-30B-GGUF with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use NANI-Nithin/Muse-Glimmer-30B-GGUF with OpenClaw:

Start the llama.cpp server

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

Lemonade

How to use NANI-Nithin/Muse-Glimmer-30B-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use NANI-Nithin/Muse-Glimmer-30B-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 NANI-Nithin/Muse-Glimmer-30B-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 NANI-Nithin/Muse-Glimmer-30B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

Muse-Glimmer-30B-GGUF

High-quality GGUF quantizations of Meta's Muse Glimmer 30B.

This repository provides production-ready GGUF files converted directly from the official Muse Glimmer 30B Hugging Face release and quantized using the latest llama.cpp tooling.

Quick Download

Quant	File
IQ3_M	Muse-Glimmer-30B-IQ3_M.gguf
IQ4_XS	Muse-Glimmer-30B-IQ4_XS.gguf
IQ4_NL	Muse-Glimmer-30B-IQ4_NL.gguf
Q4_K_M	Muse-Glimmer-30B-Q4_K_M.gguf
Q5_K_M	Muse-Glimmer-30B-Q5_K_M.gguf
Q6_K	Muse-Glimmer-30B-Q6_K.gguf
Q8_0	Muse-Glimmer-30B-Q8_0.gguf
F16	Muse-Glimmer-30B-F16.gguf

Model Details

Model: Muse Glimmer 30B
Architecture: MuseGlimmerForConditionalGeneration
Parameters: 30B
Context Length: 131,072
Modalities: Text + Image
Base Model: meta-models/Muse-Glimmer-30B
GGUF Conversion: llama.cpp
License: Apache 2.0

Available Quantizations

IQ3_M

Excellent low-memory option with good quality retention.

Approximate size:

14-15 GB

Recommended for:

16 GB Macs
24 GB GPUs
Memory-constrained deployments

IQ4_XS

High efficiency quantization with strong quality-per-GB.

Approximate size:

16-17 GB

Recommended for:

Apple Silicon
RTX 4090
RTX 5090
LM Studio users

IQ4_NL

Premium IQ quant focused on maintaining model quality at reduced size.

Approximate size:

17-18 GB

Recommended for:

Users seeking maximum quality under 20 GB
Apple Silicon deployments
Long-context workflows

Q4_K_M

Recommended for most users.

Approximate size:

17-19 GB

Q5_K_M

Higher quality with moderate memory increase.

Approximate size:

20-22 GB

Q6_K

Near-lossless quantization.

Approximate size:

24-26 GB

Q8_0

Maximum quantized quality.

Approximate size:

31-33 GB

F16

Full precision GGUF.

Approximate size:

55-58 GB

Recommended Downloads

Use Case	Recommended Quant
Lowest Memory Usage	IQ3_M
Best Efficiency	IQ4_XS
Best Quality Below 20 GB	IQ4_NL
General Purpose	Q4_K_M
High Quality	Q5_K_M
Near Lossless	Q6_K
Maximum Quantized Quality	Q8_0
Full Precision	F16

Features

Muse Glimmer is designed for:

Agentic task execution
Coding and software engineering
Long-context reasoning
Function calling
Tool use
Screenshot understanding
Document understanding
Multimodal reasoning
Vision-language tasks
Local AI deployment

Runtime Compatibility

Tested or intended for:

llama.cpp
LM Studio
Open WebUI
Jan
KoboldCpp
Text Generation WebUI

llama.cpp Example

./llama-cli \
  -m Muse-Glimmer-30B-Q4_K_M.gguf \
  -c 131072

Hardware Recommendations

IQ3_M

Apple Silicon 16 GB+
RTX 4080 / 4090
24 GB GPUs

IQ4_XS

Apple Silicon 24 GB+
RTX 4090
RTX 5090

IQ4_NL

Apple Silicon 24 GB+
RTX 4090
RTX 5090

Q4_K_M

Apple Silicon 32 GB+
RTX 4090
RTX 5090

Q5_K_M

24 GB+ VRAM
Apple Silicon 48 GB+

Q6_K

32 GB+ available memory

Q8_0

40 GB+ available memory

F16

58 GB+ available memory

Conversion Information

Generated from:

meta-models/Muse-Glimmer-30B

Conversion pipeline:

HF Safetensors
→ GGUF F16
→ IQ / Q Quantization

Generated using native Muse Glimmer support in llama.cpp.

No fine-tuning, retraining, merging, alignment modifications, or architecture changes have been applied.

Available Files

Muse-Glimmer-30B-IQ3_M.gguf
Muse-Glimmer-30B-IQ4_XS.gguf
Muse-Glimmer-30B-IQ4_NL.gguf
Muse-Glimmer-30B-Q4_K_M.gguf
Muse-Glimmer-30B-Q5_K_M.gguf
Muse-Glimmer-30B-Q6_K.gguf
Muse-Glimmer-30B-Q8_0.gguf
Muse-Glimmer-30B-F16.gguf

SEO Keywords

Muse Glimmer GGUF, Muse Glimmer 30B GGUF, Muse Glimmer IQ3_M, Muse Glimmer IQ4_XS, Muse Glimmer IQ4_NL, Muse Glimmer Q4_K_M, Muse Glimmer Q5_K_M, Muse Glimmer Q6_K, Muse Glimmer Q8_0, Muse Glimmer llama.cpp, Muse Glimmer LM Studio, Muse Glimmer Open WebUI, Muse Glimmer local AI, Muse Glimmer multimodal, Muse Glimmer vision model, Muse Glimmer Apple Silicon, Muse Glimmer Mac.

Credits

Meta Superintelligence Labs for Muse Glimmer.
ggml-org for llama.cpp.
Hugging Face for model hosting.

License

Apache 2.0.

Please also follow the original model license and usage policy provided with the base model.

Base model:

meta-models/Muse-Glimmer-30B

Downloads last month: -

GGUF

Model size

28B params

Architecture

muse-glimmer

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for NANI-Nithin/Muse-Glimmer-30B-GGUF

Base model

meta-models/Muse-Glimmer-30B

Quantized

(84)

this model