Instructions to use GadflyII/Qwen3-VL-235B-A22B-Thinking-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GadflyII/Qwen3-VL-235B-A22B-Thinking-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="GadflyII/Qwen3-VL-235B-A22B-Thinking-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("GadflyII/Qwen3-VL-235B-A22B-Thinking-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("GadflyII/Qwen3-VL-235B-A22B-Thinking-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 GadflyII/Qwen3-VL-235B-A22B-Thinking-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GadflyII/Qwen3-VL-235B-A22B-Thinking-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": "GadflyII/Qwen3-VL-235B-A22B-Thinking-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/GadflyII/Qwen3-VL-235B-A22B-Thinking-NVFP4

SGLang

How to use GadflyII/Qwen3-VL-235B-A22B-Thinking-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 "GadflyII/Qwen3-VL-235B-A22B-Thinking-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": "GadflyII/Qwen3-VL-235B-A22B-Thinking-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 "GadflyII/Qwen3-VL-235B-A22B-Thinking-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": "GadflyII/Qwen3-VL-235B-A22B-Thinking-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 GadflyII/Qwen3-VL-235B-A22B-Thinking-NVFP4 with Docker Model Runner:
```
docker model run hf.co/GadflyII/Qwen3-VL-235B-A22B-Thinking-NVFP4
```

Qwen3-VL-235B-A22B-Thinking-NVFP4

NVFP4 (4-bit floating point) quantized version of Qwen/Qwen3-VL-235B-A22B-Thinking, optimized for NVIDIA Blackwell GPUs.

This is the Thinking variant with enhanced reasoning capabilities.

Model Details

Property	Value
Base Model	Qwen/Qwen3-VL-235B-A22B-Thinking-2507
Parameters	235B (22B active per token)
Architecture	MoE (Mixture of Experts) + Vision
Quantization	NVFP4 (weights & activations)
Original Size	~471 GB (BF16)
Quantized Size	~127 GB
Compression	~3.7x

Quantization Details

Tool: llmcompressor
Scheme: NVFP4 (4-bit floating point with block-wise scaling)
Calibration: 512 samples, 4096 sequence length
Pipeline: Sequential (layer-by-layer for memory efficiency)
Preserved layers: embeddings, lm_head, vision encoder, MoE gates/routers

Hardware Requirements

Minimum VRAM: ~130 GB (TP=2 recommended)
Optimized for: NVIDIA Blackwell (SM120) - RTX 5090, RTX PRO 6000
Also works on: NVIDIA Hopper (SM90) - H100, H200

Usage with vLLM

# Environment variables for Blackwell GPUs
export VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8_CUTLASS=1
export VLLM_FLASH_ATTN_VERSION=2

# Serve with tensor parallelism
vllm serve GadflyII/Qwen3-VL-235B-A22B-Thinking-NVFP4 \
  --tensor-parallel-size 2 \
  --trust-remote-code \
  --max-model-len 32768

Performance

Tested on 2x NVIDIA RTX PRO 6000 Blackwell (192GB VRAM total) with vLLM 0.13.0:

Metric	Value
Single Request Decode	57 tokens/s
Batch Throughput (8 req)	277 tokens/s
Memory Usage	~128 GB (64 GB/GPU)

Acknowledgments

Original model by Qwen Team
Quantization using vLLM llmcompressor

License

Apache 2.0 (same as base model)

Downloads last month: 37

Safetensors

Model size

133B params

Tensor type

BF16

F32

F8_E4M3

Model tree for GadflyII/Qwen3-VL-235B-A22B-Thinking-NVFP4

Base model

Qwen/Qwen3-VL-235B-A22B-Thinking

Quantized

(15)

this model