Instructions to use Qwen/Qwen3-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3-4B with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen3-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen3-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3-4B

SGLang

How to use Qwen/Qwen3-4B 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 "Qwen/Qwen3-4B" \
    --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": "Qwen/Qwen3-4B",
		"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 "Qwen/Qwen3-4B" \
        --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": "Qwen/Qwen3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen3-4B with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3-4B
```

Why are the new 4B and 8B models slower than the previous 7B-1M model??

by stev236 - opened May 7, 2025

Discussion

stev236

May 7, 2025

•

edited May 7, 2025

The documentation says that this new version should produce better quality results than version 2.5.
I don't really see any quality improvement to my summaries (some are not as good), but more importantly, the inference speed of both the new 4B and 8B models is slower than that of the old 7B model.

I'm using vLLM, on 4x RTX 3060, weight-only FP8 compression using the Marlin kernel, 'enable_thinking=False', and tried with batchsize 1 and batchsize 4 with similar results. Below is the output from VLLM for summarizing a text of about 28k tokens. I ran each task twice. I presume the second run is always much faster because of some prefix caching. Anyway, the new 4B model is slightly slower than the 7B model on the first run, and terribly worse on the second repetition. The new 8B model takes almost twice as long as the old 7B on the first run, and is also much slower on the second run. Below is the vLLM output:

Qwen2.5-7b-1M:
[00:13<00:00, 13.75s/it, est. speed input: 2063.93 toks/s, output: 14.69 toks/s] (first run)
[00:02<00:00, 2.23s/it, est. speed input: 12732.36 toks/s, output: 87.04 toks/s] (second run)

Qwen3-4b:
[00:14<00:00, 14.45s/it, est. speed input: 1964.26 toks/s, output: 16.96 toks/s] (first run)
[00:03<00:00, 3.92s/it, est. speed input: 7249.40 toks/s, output: 62.58 toks/s] (second run)

Qwen3-8b: about 3.4 second
[00:20<00:00, 20.77s/it, est. speed input: 1366.44 toks/s, output: 8.62 toks/s] (first run)
[00:02<00:00, 2.94s/it, est. speed input: 9656.35 toks/s, output: 60.90 toks/s] (second run)

Did anybody else notice that the new 4b and 8b models are slower than the old 7b-1M model?
Am I doing something wrong or missing something?

Thanks to the Qwen team for the awesome 7B-1M model, and to anybody who can help me understand what's going on.

that0ne

May 13, 2025

How do you use it? List your setting parameters. This qwen3 model is very sensitive to parameter Settings

metalure

May 18, 2025

cause more layers?

ZiggyS

May 18, 2025

Improvement of results often times means a bit of a loss of speed. Just the nature of things.

stev236 changed discussion status to closed Aug 2, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment