Instructions to use Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32")
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("Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32")
model = AutoModelForMultimodalLM.from_pretrained("Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32", 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 Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32",
		"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/Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32

SGLang

How to use Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32 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 "Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32" \
    --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": "Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32",
		"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 "Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32" \
        --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": "Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32",
		"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 Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32 with Docker Model Runner:
```
docker model run hf.co/Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32
```

Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32 / README.md

Disty0

Update README.md

cf9ca95 verified 9 months ago

2.1 kB

license: apache-2.0
base_model:
  - Qwen/Qwen3-VL-32B-Instruct
base_model_relation: quantized
library_name: transformers
tags:
  - sdnq
  - qwen3_vl
  - 4-bit

4 bit (UINT4 with SVD rank 32) quantization of Qwen/Qwen3-VL-32B-Instruct using SDNQ.

Usage:

pip install git+https://github.com/Disty0/sdnq

import torch
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor

model_path = "Disty0/Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32"

# default: Load the model on the available device(s)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_path, dtype=torch.bfloat16, device_map="auto"
)

# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
# model = Qwen3VLForConditionalGeneration.from_pretrained(
#     model_path,
#     dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

processor = AutoProcessor.from_pretrained(model_path)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

# Preparation for inference
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)
inputs = inputs.to(model.device)

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)