Instructions to use Qwen/Qwen3-Coder-480B-A35B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3-Coder-480B-A35B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen3-Coder-480B-A35B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Coder-480B-A35B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Coder-480B-A35B-Instruct")
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
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen3-Coder-480B-A35B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3-Coder-480B-A35B-Instruct"
# 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-Coder-480B-A35B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3-Coder-480B-A35B-Instruct

SGLang

How to use Qwen/Qwen3-Coder-480B-A35B-Instruct 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-Coder-480B-A35B-Instruct" \
    --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-Coder-480B-A35B-Instruct",
		"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-Coder-480B-A35B-Instruct" \
        --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-Coder-480B-A35B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen3-Coder-480B-A35B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3-Coder-480B-A35B-Instruct
```

Update chat_template and tool_parser

#27

by rshcao - opened Aug 21, 2025

base: refs/heads/main

←

from: refs/pr/27

Discussion Files changed

+438

-307

rshcao

Qwen org Aug 21, 2025

support arbitrary XLM-format tool keys definition;
support more robust arrary/dict-type tool call arguments serialization;
revise the tool_parser to cater to the changes in chat_template, and remove insafe eval operations.

Update chat_template and tool_parser75b6d96b

cyente changed pull request status to merged Aug 21, 2025

nbroad

Aug 29, 2025

•

edited Aug 29, 2025

This parser is nearly identical to the one in vllm: https://github.com/vllm-project/vllm/blob/b7adf94c4a6c7290dd8765819da68a801008f5a1/vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py

Is the one in this repo the recommended one to use?

~~If so, is there a way to load this parser when launching vllm?~~
--tool-parser-plugin "path/to/parser.py"

I'm just using --tool-call-parser qwen3_coder currently

rshcao

Qwen org Sep 2, 2025

We have made pulling request to the vLLM team, and actively urge to use exactly the same parser with this Huggingface repo (the parser in this HF repo is a newer version).

Before vLLM merging, you can also load this parser manually with vLLM using:

--enable-auto-tool-choice --tool-call-parser qwen3_coder --tool-parser-plugin "path/to/this/hf_repo/parser.py" --chat-template "path/to/this/hf_repo/chat_template.jinja"

nbroad

Sep 2, 2025

Thank you!

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