Instructions to use prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX")
model = AutoModelForImageTextToText.from_pretrained("prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX")
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

vLLM

How to use prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX",
		"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/prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX

SGLang

How to use prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX 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 "prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX" \
    --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": "prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX",
		"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 "prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX" \
        --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": "prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX",
		"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 prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3-VL-4B-Instruct-Unredacted-MAX

Qwen3-VL-4B-Instruct-Unredacted-MAX is an optimized release built on top of huihui-ai/Qwen3-VL-4B-Instruct-abliterated. This version focuses on updated packaging, improved Transformers compatibility, and stable multimodal inference behavior, while preserving the core vision-language reasoning capabilities of the original architecture. The result is a capable 4B vision-language model designed for efficient deployment, research workflows, and multimodal experimentation.

Key Highlights

Optimized Release Structure Streamlined repository organization for easier loading, deployment, and inference workflows.
Modern Transformers Compatibility Updated for stable integration with recent Hugging Face Transformers versions.
4B Vision-Language Architecture Built on Qwen3-VL-4B-Instruct, balancing multimodal capability with efficient compute requirements.
Stable Multimodal Inference Designed for consistent performance across image-text understanding tasks.
Efficient Caption Generation Produces structured and detailed descriptions suitable for annotation and dataset pipelines.
Dynamic Resolution Support Retains native support for varying image resolutions and aspect ratios.

Base Model Signatures:

This model has been re-sharded and optimized for the latest Transformers version from the base model: https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated

Quick Start with Transformers

from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen3VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX",
    torch_dtype="auto",
    device_map="auto"
)

processor = AutoProcessor.from_pretrained(
    "prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX"
)

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

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

image_inputs, video_inputs = process_vision_info(messages)

inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
).to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)

output_text = processor.batch_decode(
    [out[len(inp):] for inp, out in zip(inputs.input_ids, generated_ids)],
    skip_special_tokens=True,
    clean_up_tokenization_spaces=False
)

print(output_text)

Intended Use

Multimodal research and vision-language evaluation
Image captioning and dataset generation pipelines
Prototyping AI systems combining text and vision
Lightweight deployment on consumer or mid-range GPUs
Experimental workflows in multimodal understanding

Limitations & Risks

Important Note: This model inherits constraints and behavior from its base architecture.

Output quality depends heavily on image clarity and prompt design
May produce incomplete or inconsistent interpretations in complex scenarios
Requires sufficient GPU memory for stable inference
Performance varies with decoding settings and runtime optimization

Downloads last month: 850

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

(288)

this model

Quantizations

5 models

Spaces using prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX 6

Collection including prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX

Unredacted MAX - VL

Collection

multi-stage trained continual "abliteration" approach for the qwen3-vl series models • 5 items • Updated Apr 27 • 5