Instructions to use kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-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 kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-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 kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

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 kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

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 kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

Use Docker

docker model run hf.co/kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

LM Studio
Jan

vLLM

How to use kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-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": "kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-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/kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

Ollama
How to use kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF with Ollama:
```
ollama run hf.co/kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16
```

Unsloth Studio

How to use kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-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 kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-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 kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF to start chatting

How to use kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

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": "kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16
```

Lemonade

How to use kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

Run and chat with the model

lemonade run user.Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-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 kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

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 kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16

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 "kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF:BF16" \
  --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"

⚠️ STOCK llama.cpp WILL NOT LOAD THIS MODEL

muse-glimmer is not an upstream architecture, and these are ROCmFPX quant types. The complete port is in patches/ on the 4-bit repo.

⚠️ -fa off is required — flash attention breaks the vision path on gfx1151.

27.23 GiB · 11.31 t/s prose / 39.35 t/s code (with DFlash) on a Ryzen AI MAX+ 395.

Muse-Glimmer-30B — ROCmFPX 8-bit AGENT GGUF

Quantized from BF16 GGUF (55,725,514,112 B) — a lossless source, not a requantization.


File	`muse-glimmer-30B-Q8_0_ROCMFPX_AGENT.gguf`
Size	27.23 GiB (29,235,965,312 B)
BPW	8.39
ftype	`Q8_0_ROCMFPX_AGENT` (115)

Its speculative head is DFlash, not MTP — read mean acceptance length, and do not use MTP flags with it.

All quant variants

⚠️ Decode on this model is workload-dominated, not variant-dominated. DFlash proposes long runs on repetitive/code text and very little on freeform prose, so a single tok/s number is misleading. Measured on one Ryzen AI MAX+ 395, median of 3, -fa on, with the DFlash head (--spec-type draft-dflash --model-draft dflash-ROCmFP4-STRIX.gguf --spec-draft-ngl 99):

variant	ftype	size	prose	code-transform	acceptance len (code)
4-bit FAST	103	13.80 GiB	15.07	39.35 t/s	7.12
4-bit STRIX	105	14.17 GiB	14.96	37.55 t/s	6.80
8-bit plain	111	26.85 GiB	11.31	—	2.65
8-bit AGENT	115	27.23 GiB	11.27	—	2.51

The 2.6× spread between prose and code is the same model and the same binary — acceptance length moves 2.9 → 7.1. Quote a range for this model, not a point.

⛔ Serve it with the draft head. Without --model-draft the 8-bit build drops 11.62 → 7.65 (−34%). ⚠️ -fa off is required only for the vision path; text-only can run -fa on.

The two 8-bit builds are within noise of each other — AGENT lifts draft acceptance on MTP models, and this one uses DFlash, so there is nothing for it to win here.

What was NOT measured

No perplexity run, no quality A/B against the source.
No long-context testing. · No tool-calling evaluation.

Base model licence inherited; credit goes to its authors.

Downloads last month: 139

GGUF

Model size

28B params

Architecture

muse-glimmer

Hardware compatibility

8-bit

Model tree for kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF

Base model

meta-models/Muse-Glimmer-30B

Quantized

(142)

this model

kingjones777
/

Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF

⚠️ STOCK `llama.cpp` WILL NOT LOAD THIS MODEL

Muse-Glimmer-30B — ROCmFPX 8-bit AGENT GGUF

All quant variants

What was NOT measured

Model tree for kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF

⚠️ STOCK llama.cpp WILL NOT LOAD THIS MODEL

Muse-Glimmer-30B — ROCmFPX 8-bit AGENT GGUF

All quant variants

What was NOT measured

Model tree for kingjones777/Muse-Glimmer-30B-ROCmFPX-Q8_0-AGENT-GGUF

⚠️ STOCK `llama.cpp` WILL NOT LOAD THIS MODEL