Instructions to use Vishva007/Muse-Glimmer-30B-W2A16-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vishva007/Muse-Glimmer-30B-W2A16-AutoRound with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Vishva007/Muse-Glimmer-30B-W2A16-AutoRound")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Vishva007/Muse-Glimmer-30B-W2A16-AutoRound")
model = AutoModelForMultimodalLM.from_pretrained("Vishva007/Muse-Glimmer-30B-W2A16-AutoRound", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vishva007/Muse-Glimmer-30B-W2A16-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vishva007/Muse-Glimmer-30B-W2A16-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vishva007/Muse-Glimmer-30B-W2A16-AutoRound",
		"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/Vishva007/Muse-Glimmer-30B-W2A16-AutoRound

SGLang

How to use Vishva007/Muse-Glimmer-30B-W2A16-AutoRound with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Vishva007/Muse-Glimmer-30B-W2A16-AutoRound" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vishva007/Muse-Glimmer-30B-W2A16-AutoRound",
		"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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Vishva007/Muse-Glimmer-30B-W2A16-AutoRound" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vishva007/Muse-Glimmer-30B-W2A16-AutoRound",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Vishva007/Muse-Glimmer-30B-W2A16-AutoRound with Docker Model Runner:
```
docker model run hf.co/Vishva007/Muse-Glimmer-30B-W2A16-AutoRound
```

Muse Glimmer 30B - W2A16 AutoRound / GPTQ

This repository contains the W2A16 quantized versions of Meta's Muse Glimmer 30B, optimized for extreme memory efficiency during local inference. The model was quantized using Intel AutoRound to 2-bit precision. To preserve the model's multimodal and agentic capabilities, the Vision Encoder was explicitly kept in its original precision (BF16).

Two formats are provided across the repositories:

AutoRound Format: Vishva007/Muse-Glimmer-30B-W2A16-AutoRound
AutoGPTQ Format: Vishva007/Muse-Glimmer-30B-W2A16-AutoRound-GPTQ

Quantization Details

The quantization was performed with high-accuracy calibration settings tailored for 2-bit compression:

Scheme: W2A16 (2-bit weights, 16-bit activations)
Group Size: 32 (Lowered to preserve accuracy in 2-bit)
Symmetric: True
Iterations: 1000
Vision Module: Kept unquantized (quant_nontext_module=False) to ensure maximum vision-language alignment.
Calibration: 512 samples, sequence length of 2048.

By compressing the language model weights to 2-bit precision, this version vastly reduces VRAM requirements, leaving ample room for the KV cache and the unquantized perception encoder to run smoothly on lower-VRAM consumer GPUs.

Usage with vLLM

For optimal performance, including agentic function calling and reasoning parsing, use the vllm/vllm-openai:muse-glimmer image or the latest vLLM build supporting Muse Glimmer.

Run the following command to serve the model (adjust the model path to the AutoRound or GPTQ repo as needed):

vllm serve Vishva007/Muse-Glimmer-30B-W2A16-AutoRound \
  --served-model-name muse-glimmer \
  --gpu-memory-utilization 0.90 \
  --max-model-len 32768 \
  --max-num-seqs 128 \
  --generation-config auto \
  --enable-auto-tool-choice \
  --tool-call-parser muse_glimmer \
  --reasoning-parser muse_glimmer

Key vLLM Flags Explained

--max-model-len 32768: Sets the context window to 32k tokens.
--enable-auto-tool-choice: Enables agentic tool selection.
--tool-call-parser / --reasoning-parser: Configures the endpoint to natively handle Muse Glimmer's multi-step thinking and function schema outputs.

About the Base Model (Muse Glimmer 30B)

Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder (~1.8B param ViT-G/14), distilled from Muse Spark by Meta Superintelligence Lab. It is purpose-built for autonomous agentic tasks on consumer hardware.

Key Capabilities:

End-to-end Agentic Task Completion: High success rates on DeepSearch QA, MCP-Atlas, 𝛕3-Bench, and SWE-Bench.
Multimodal Reasoning: Interprets interleaved text and images (charts, documents, screenshots).
Reliable Tool Use & Failure Recovery: Handles complex tool schemas and automatically diagnoses/retries failed calls.
Controllable Effort: Supports customizable reasoning strengths (low/medium/high/xhigh) via system prompts.
Multilingual: Trained on data from more than 100 languages.

License: Apache 2.0

Downloads last month: -

Safetensors

Model size

5B params

Tensor type

BF16

I32

F16

Model tree for Vishva007/Muse-Glimmer-30B-W2A16-AutoRound

Base model

meta-models/Muse-Glimmer-30B

Quantized

(95)

this model

Collection including Vishva007/Muse-Glimmer-30B-W2A16-AutoRound

Meta's Muse Glimmer

Collection

Quantized Muse Glimmer models for efficient image-text understanding (AutoRound W4A16 and W2A16). • 4 items • Updated about 21 hours ago