Note: Note: When launching with 8 GPUs, --enable-expert-parallel must be specified; otherwise, the expert tensors cannot be evenly split across tensor parallel ranks. This option is not required for 4-GPU setups.

CONTEXT_LENGTH=32768  # 262144

vllm serve \
    QuantTrio/Qwen3-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8Mix \
    --served-model-name Qwen3-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

【Dependencies】

vllm>=0.9.2

【Model Update History】

2025-08-19
1.[BugFix] Fix compatibility issues with vLLM 0.10.1

2025-08-11
1.Upload tokenizer_config.json

2025-08-01
1. upload the missing 00001, 00003, 00006 weight files

2025-07-24
1. fast commit

【Model Files】

File Size	Last Updated
`261GB`	`2025-07-24`

【Model Download】

python

from huggingface_hub import snapshot_download
snapshot_download('QuantTrio/Qwen3-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Description】

Qwen3-Coder-480B-A35B-Instruct

Highlights

Today, we're announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we're excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct. featuring the following key enhancements:

Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks, achieving results comparable to Claude Sonnet.
Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding.
Agentic Coding supporting for most platfrom such as Qwen Code, CLINE, featuring a specially designed function call format.

Model Overview

Qwen3-480B-A35B-Instruct has the following features:

Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 480B in total and 35B activated
Number of Layers: 62
Number of Attention Heads (GQA): 96 for Q and 8 for KV
Number of Experts: 160
Number of Activated Experts: 8
Context Length: 262,144 natively.

NOTE: This model supports only non-thinking mode and does not generate <think></think> blocks in its output. Meanwhile, specifying enable_thinking=False is no longer required.

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.

Quickstart

We advise you to use the latest version of transformers.

With transformers<4.51.0, you will encounter the following error:

KeyError: 'qwen3_moe'

The following contains a code snippet illustrating how to use the model generate content based on given inputs.

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen3-480B-A35B-Instruct"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Write a quick sort algorithm."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=65536
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

content = tokenizer.decode(output_ids, skip_special_tokens=True)

print("content:", content)

Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value, such as 32,768.

For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.

Agentic Coding

Qwen3-Coder excels in tool calling capabilities.

You can simply define or use any tools as following example.

python

# Your tool implementation
def square_the_number(num: float) -> dict:
    return num ** 2

# Define Tools
tools=[
    {
        "type":"function",
        "function":{
            "name": "square_the_number",
            "description": "output the square of the number.",
            "parameters": {
                "type": "object",
                "required": ["input_num"],
                "properties": {
                    'input_num': {
                        'type': 'number', 
                        'description': 'input_num is a number that will be squared'
                        }
                },
            }
        }
    }
]

import OpenAI
# Define LLM
client = OpenAI(
    # Use a custom endpoint compatible with OpenAI API
    base_url='http://localhost:8000/v1',  # api_base
    api_key="EMPTY"
)
 
messages = [{'role': 'user', 'content': 'square the number 1024'}]

completion = client.chat.completions.create(
    messages=messages,
    model="Qwen3-480B-A35B-Instruct",
    max_tokens=65536,
    tools=tools,
)

print(completion.choice[0])

Best Practices

To achieve optimal performance, we recommend the following settings:

Sampling Parameters:
- We suggest using temperature=0.7, top_p=0.8, top_k=20, repetition_penalty=1.05.
Adequate Output Length: We recommend using an output length of 65,536 tokens for most queries, which is adequate for instruct models.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}