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

Libraries

How to use yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-NVFP4 with Transformers:

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

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-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": "yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-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/yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-NVFP4

SGLang

How to use yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-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 "yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-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": "yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-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 "yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-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": "yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-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 yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-NVFP4 with Docker Model Runner:
```
docker model run hf.co/yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-NVFP4
```

Muse-Glimmer-30B-Abliterated-Aggressive — NVFP4 (lean, vision-preserved)

A lean 22 GB NVFP4 (W4A4) quant of jorkle/Muse-Glimmer-30B-Abliterated-Aggressive (itself an aggressively-decensored — KL-conserving LoRA-SFT — build of Meta's meta-models/Muse-Glimmer-30B).

Built to run a decensored, vision-preserving Muse-Glimmer on a single ~24–32 GB Blackwell / DGX-Spark (GB10) in vLLM. At the time of quanting, no decensored lean NVFP4 Muse existed — the public lean NVFP4s were the censored base, and the decensored builds were only GGUF / bf16 / MLX / a fat 28 GB NVFP4. This fills that gap.

What it is

Format: compressed-tensors NVFP4, W4A4 group-16, via Intel AutoRound (scheme="NVFP4", dataset="NeelNanda/pile-10k", nsamples=128, seqlen=2048, iters=200, quant_nontext_module=False).
Vision tower + lm_head kept in BF16 (quant_nontext_module=False) — pristine multimodal input at zero decode cost; only the decoder Linear layers (the size + per-token bandwidth) are quantized to FP4.
~22 GB on disk (vs the ~28 GB fat abliterated NVFP4). Multimodal (perception encoder) intact.

Serving (vLLM)

Needs a Muse-Glimmer-capable vLLM build (e.g. vllm/vllm-openai:muse-glimmer):

vllm serve <this-model> --served-model-name muse-aggressive \
  --reasoning-parser muse_glimmer --enable-auto-tool-choice --tool-call-parser muse_glimmer \
  --trust-remote-code --max-model-len 131072 --kv-cache-dtype fp8

Quantization auto-detects (compressed-tensors) — no --quantization flag needed. Use a Reasoning strength: low system line if you want content in content rather than reasoning_content.

Measured on GB10 (DGX-Spark, 224 GB/s, single-stream)

Metric	Value
Decode (c=1 / c=4 / c=8)	12.5 / 46 / 87 tok/s
HumanEval (pass@1, reasoning-low)	.872
IFEval (prompt-level strict)	.684
Tools (32-case)	.656
Vision	✅ (accurately describes real images)

Honest notes

This is the aggressive decensor. Its KL-LoRA-SFT decensoring lowers instruction-following (IFEval .684) vs a plain weight-edit abliteration of the same base (which measured IFEval ~.90). Prefer this build for maximally-permissive / RP use; for instruction-following-critical work a manual-abliterated quant is better.
Speed is bandwidth-bound (dense 30B ÷ ~224 GB/s). No speculative drafter is included — pairing a matched DFlash/EAGLE drafter would roughly double decode.

Attribution

Base: Meta Muse-Glimmer-30B. Decensoring: jorkle (Abliterated-Aggressive, KL-LoRA-SFT). NVFP4 quant: this repo (AutoRound, compressed-tensors). Inherits the upstream Muse-Glimmer license.

Downloads last month: 37

Safetensors

Model size

19B params

Tensor type

BF16

Model tree for yar-sh/Muse-Glimmer-30B-Abliterated-Aggressive-NVFP4

Base model

meta-models/Muse-Glimmer-30B

Adapter

jorkle/Muse-Glimmer-30B-Abliterated-Aggressive

Quantized

(1)

this model