Instructions to use Preyazz/Muse-Glimmer-30B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Preyazz/Muse-Glimmer-30B-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Preyazz/Muse-Glimmer-30B-NVFP4")
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("Preyazz/Muse-Glimmer-30B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("Preyazz/Muse-Glimmer-30B-NVFP4", 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 Preyazz/Muse-Glimmer-30B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Preyazz/Muse-Glimmer-30B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Preyazz/Muse-Glimmer-30B-NVFP4",
		"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/Preyazz/Muse-Glimmer-30B-NVFP4

SGLang

How to use Preyazz/Muse-Glimmer-30B-NVFP4 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 "Preyazz/Muse-Glimmer-30B-NVFP4" \
    --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": "Preyazz/Muse-Glimmer-30B-NVFP4",
		"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 "Preyazz/Muse-Glimmer-30B-NVFP4" \
        --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": "Preyazz/Muse-Glimmer-30B-NVFP4",
		"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 Preyazz/Muse-Glimmer-30B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Preyazz/Muse-Glimmer-30B-NVFP4
```

Muse-Glimmer-30B — NVFP4 (compressed-tensors)

A 4-bit NVFP4 quantization of meta-models/Muse-Glimmer-30B, in compressed-tensors format, for local serving on NVIDIA GB10 / DGX Spark (Blackwell sm_121, native FP4). Language model shrinks 56 GB → 22 GB and runs in vLLM at ~13 tok/s single-stream.

Recipe

Weight-only NVFP4 (E2M1, 16-element blocks, per-tensor + per-block f8e4m3 scales) on the language-model linears only. The perception encoder is retained in bf16, so image input still works.

Component	Precision
LM attention `q/k/v/o/gate_proj` (52 layers)	NVFP4
LM MLP `gate/up/down_proj` (52 layers)	NVFP4
Vision tower / adapter / projection	bf16
`embed_tokens`, `lm_head`, all norms	bf16

416 linears quantized, mean weight round-trip error ~9.5% (expected for E2M1).
Format: compressed-tensors · nvfp4-pack-quantized · group_size: 16 · W4A16 (weight-only).

Serving (vLLM on GB10)

muse_glimmer support lands via vllm-project/vllm#51655 (native model + reasoning/tool parsers + DFlash speculative decoding). Until it merges upstream, build vLLM from that branch:

git clone -b tiezhen/new-model-support https://github.com/xianbaoqian/vllm && cd vllm
VLLM_USE_PRECOMPILED=1 pip install -e .          # precompiled kernels; no full CUDA build

export PATH="$VENV/bin:/usr/local/cuda/bin:$PATH"   # venv bin on PATH so vLLM's JIT finds `ninja`
vllm serve <this-repo> --served-model-name muse --trust-remote-code \
  --max-model-len 8192 --gpu-memory-utilization 0.9 \
  --reasoning-parser muse_glimmer --tool-call-parser muse_glimmer

The reasoning parser is required — muse uses channel-scoped output framing (not <think> tags) and forces skip_special_tokens=False; without it the channels collapse and output is empty.

Performance

1× DGX Spark (GB10), vLLM, greedy, batch size 1:

Config	tok/s
CUDA graphs (default)	13.0
`--enforce-eager`	11.5

Decode is memory-bound — the speedup tracks the 56→22 GB weight reduction, and CUDA graphs add only ~13% (launch overhead). Pair with the DFlash drafter for ~3× on decode.

Validation

Smoke-verified with greedy generation on the vLLM branch above — coherent output with correct stop tokens. Full accuracy suite not yet run.

Provenance

Quantized with a pure-torch (CPU) compressed-tensors NVFP4 converter directly from the bf16 safetensors — weight-only, no calibration data. Base model © Meta Superintelligence Lab (Apache-2.0).

Downloads last month: -

Safetensors

Model size

30B params

Tensor type

BF16

Model tree for Preyazz/Muse-Glimmer-30B-NVFP4

Base model

meta-models/Muse-Glimmer-30B

Quantized

(63)

this model