Instructions to use QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-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 QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-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 QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

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 QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

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 QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

Use Docker

docker model run hf.co/QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

LM Studio
Jan

vLLM

How to use QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-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": "QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

Ollama
How to use QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF with Ollama:
```
ollama run hf.co/QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0
```
Unsloth Desktop

How to use QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

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": "QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF with Docker Model Runner:
```
docker model run hf.co/QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0
```

Lemonade

How to use QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

Run and chat with the model

lemonade run user.Muse-Glimmer-30B-QUASAR-Q4_0-GGUF-Q4_0

List all available models

lemonade list

Hermes Agent

How to use QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-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 QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

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 QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0

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 "QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF:Q4_0" \
  --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"

Muse Glimmer 30B — native Q4_0 QAT for llama.cpp

Native Q4_0 quantization-aware training with QUASAR. On held-out response tokens, this checkpoint is closer to BF16 than Meta's official Q4_K_M GGUF: 0.0213 vs 0.0228 KL and 95.9% vs 95.6% top-1 agreement, while training all 416 decoder projections directly on the standard Q4_0 lattice.

NVFP4 / vLLM · W4A4 / Blackwell · GGUF / llama.cpp (this repo) · Muse Glimmer collection · QUASAR paper

Model	Decoder format	KL to BF16 ↓	Top-1 agreement ↑
QUASAR Q4_0 (this model)	416 × Q4_0	0.0213	95.9%
Meta Q4_K_M	365 × Q4_K + 52 × Q6_K	0.0228	95.6%

Measured on 948 held-out agentic prompts and 1.19M response tokens with the same fidelity harness.

Run it

ollama run hf.co/QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF

llama-server -hf QUASAR-QAT/Muse-Glimmer-30B-QUASAR-Q4_0-GGUF \
  -c 131072 -fa on --jinja

For LM Studio, search for QUASAR-QAT Muse-Glimmer.

Supports 131,072-token context with the embedded Muse chat template for reasoning and tool calls. Requires a llama.cpp build with Muse Glimmer support (9a4843c, September 2026, or newer). This GGUF is text-only.

Selected benchmarks

Task	QUASAR Q4_0	Meta Q4_K_M
GSM8K, 5-shot	93.2	92.4
GPQA-Diamond, 0-shot CoT	67.7	64.6

Both models were served through the same llama.cpp build with identical prompts and decoding. Full same-harness fidelity and downstream results are available in eval/.

Technical details

All 416 decoder projections were trained directly on the Q4_0 lattice with QUASAR: INT4 codes with one scale per 32-weight block. The GGUF packs the trained codes and scales directly rather than applying a separate post-training quantization pass.

The checkpoint is 19.6 GB, with Q4_0 decoder projections, F16 token embeddings and output head, F32 norms, and the Muse chat template embedded. Export fidelity is documented in native_q4_0_receipt.json.

QUASAR is loss-aware quantization-aware training: it improves low-bit reconstruction during training and exports to standard deployment formats with zero inference overhead.

NVFP4 / vLLM · NVFP4 W4A4 / Blackwell · Muse Glimmer 30B — QUASAR 4-bit QAT · Base model · QUASAR paper

Running this checkpoint? Share benchmark results, deployment notes, or integrations in Discussions.

Citation

@article{counathe2026quasar,
  title={QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction},
  author={Counathe, Vincent and Athiwaratkun, Ben and De Sa, Christopher and Zhang, Tianyi},
  journal={arXiv preprint arXiv:2608.13966},
  year={2026}
}