Instructions to use cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16")
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("cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16")
model = AutoModelForMultimodalLM.from_pretrained("cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16")
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 cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16",
		"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/cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16

SGLang

How to use cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16 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 "cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16" \
    --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": "cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16",
		"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 "cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16" \
        --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": "cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16",
		"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 cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16 with Docker Model Runner:
```
docker model run hf.co/cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16
```

Qwen3-VL-8B-Thinking NVFP4 W4A16

First NVFP4 Quantization of Qwen3-VL-8B-Thinking

By Mutaz Al Awamleh | ELK-AI

Model Description

This is the first publicly available NVFP4 W4A16 quantized version of Qwen3-VL-8B-Thinking, a vision-language model optimized for NVIDIA Blackwell (SM121) architecture.

Attribute	Original	NVFP4 Quantized
Parameters	8B	Same
Architecture	Vision-Language + Thinking	Same
Model Size	~17 GB	~7.1 GB
Memory Savings	-	58%
Precision	BF16	FP4 W4A16

Quick Start

Using vLLM (Recommended)

from vllm import LLM, SamplingParams

model = LLM(
    model="cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16",
    trust_remote_code=True,
    quantization="modelopt_fp4",
    kv_cache_dtype="fp8",
    gpu_memory_utilization=0.95
)

sampling_params = SamplingParams(temperature=0.7, max_tokens=512)
prompt = "Think step by step: What is shown in this image?"

outputs = model.generate([prompt], sampling_params)
print(outputs[0].outputs[0].text)

Using Docker (Pre-loaded)

# Pull the optimized container
docker pull elkaioptimization/vllm-nvfp4-cuda-13:qwen3-vl-8b-thinking-nvfp4-1.0

# Run with OpenAI-compatible API
docker run --gpus all -p 8000:8000 \
    elkaioptimization/vllm-nvfp4-cuda-13:qwen3-vl-8b-thinking-nvfp4-1.0

Quantization Details

Parameter	Value
Quantization Format	NVFP4 (FP4 E2M1)
Weight Precision	4-bit (W4)
Activation Precision	16-bit (A16)
Block Size	16 elements
Scale Format	FP8 E4M3
Calibration Dataset	CNN/DailyMail (512 samples)
Calibration Method	AWQ-style
Tool Used	NVIDIA TensorRT-Model-Optimizer

Hardware Requirements

Requirement	Minimum	Recommended
GPU	RTX 4070 (12GB)	RTX 4090 / DGX Spark
GPU Memory	12 GB	24 GB+
CUDA	12.4+	13.0
Driver	560+	570+

Model Architecture

Qwen3-VL-8B-Thinking features:

Vision-Language: Processes both images and text inputs
Enhanced Reasoning: Optimized for step-by-step thinking and complex reasoning
Extended Context: 32K native, 262K extended context length
Multilingual: Strong performance in English and Chinese

Links

Resource	Link
Original Model	Qwen/Qwen3-VL-8B-Thinking
Docker (Org)	elkaioptimization/vllm-nvfp4-cuda-13
Docker (Personal)	mutazai/vllm-spark-blackwell-nvfp4-optimized
Author	Mutaz Al Awamleh
Organization	ELK-AI

License

This model is released under the Apache 2.0 License, same as the original Qwen3 model.

Built by Mutaz Al Awamleh | ELK-AI

First to quantize Qwen3-VL-8B-Thinking to NVFP4 for Blackwell

Downloads last month: 22

Safetensors

Model size

5B params

Tensor type

BF16

F8_E4M3

Model tree for cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16

Base model

Qwen/Qwen3-VL-8B-Thinking

Quantized

(32)

this model