Instructions to use strangeropshf/qwen3-vl-4b-language_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use strangeropshf/qwen3-vl-4b-language_model with Transformers:

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

pipe = pipeline("text-generation", model="strangeropshf/qwen3-vl-4b-language_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModel

processor = AutoProcessor.from_pretrained("strangeropshf/qwen3-vl-4b-language_model")
model = AutoModel.from_pretrained("strangeropshf/qwen3-vl-4b-language_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
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 strangeropshf/qwen3-vl-4b-language_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "strangeropshf/qwen3-vl-4b-language_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "strangeropshf/qwen3-vl-4b-language_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/strangeropshf/qwen3-vl-4b-language_model

SGLang

How to use strangeropshf/qwen3-vl-4b-language_model 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 "strangeropshf/qwen3-vl-4b-language_model" \
    --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": "strangeropshf/qwen3-vl-4b-language_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "strangeropshf/qwen3-vl-4b-language_model" \
        --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": "strangeropshf/qwen3-vl-4b-language_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use strangeropshf/qwen3-vl-4b-language_model with Docker Model Runner:
```
docker model run hf.co/strangeropshf/qwen3-vl-4b-language_model
```

This is the text-only decoder component of the Qwen3-VL-4B-Instruct model. For more details, please visit the original model page or refer to the Qwen-VL technical reports published by Qwen.

Qwen3-VL-4B Language Model: The strangeropshf/qwen3-vl-4b-language_model is the extracted text-only decoder component from Qwen3-VL-4B-Instruct, featuring Qwen3's 28-layer transformer architecture with Grouped Query Attention (GQA) for efficient long-context processing up to 128K tokens, delivering near-lossless text understanding comparable to pure LLMs while maintaining seamless fusion compatibility with its DeepStack vision encoder. Optimized for multilingual instruction following across 100+ languages/dialects with strong translation capabilities, it employs interleaved rotary positional embeddings (i-MRoPE) adapted from the VL variant for robust temporal/spatial reasoning even in text-only mode, supporting advanced agentic workflows, visual coding and STEM reasoning tasks.

Quick Start with Transformers

Install the required packages

torch==2.8.0
torchvision
transformers==4.57.6
accelerate

Usage

import torch
from transformers import Qwen3VLForConditionalGeneration, AutoTokenizer

MODEL_PATH = "strangeropshf/qwen3-vl-4b-language_model"

def run_text_only_inference(model_path):

    device = "cuda" if torch.cuda.is_available() else "cpu"
    print(f"Using device: {device.upper()}")

    print("Loading tokenizer...")
    tokenizer = AutoTokenizer.from_pretrained(
        model_path,
        trust_remote_code=True
    )

    print("Loading Qwen3-VL language model...")
    model = Qwen3VLForConditionalGeneration.from_pretrained(
        model_path,
        torch_dtype=torch.bfloat16 if device == "cuda" else torch.float32,
        device_map="auto",
        trust_remote_code=True,
        use_safetensors=True
    )

    model.eval()
    print("Model loaded successfully.\n")

    prompt = "Explain what multimodal AI is in simple terms."

    inputs = tokenizer(
        prompt,
        return_tensors="pt"
    ).to(model.device)

    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=1024,
            temperature=0.7,
            do_sample=True,
            top_p=0.9
        )

    response = tokenizer.decode(outputs[0], skip_special_tokens=True)

    print("----- Response -----")
    print(response)


if __name__ == "__main__":
    run_text_only_inference(MODEL_PATH)

Downloads last month: 7

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for strangeropshf/qwen3-vl-4b-language_model

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

(271)

this model