Instructions to use Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 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-FP8")
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-FP8")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 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-FP8"
# 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-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8

SGLang

How to use Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 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-FP8" \
    --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-FP8",
		"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-FP8" \
        --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-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
```

Download Model Really slow

by yusufhadiwinata - opened Jul 26, 2025

Discussion

yusufhadiwinata

Jul 26, 2025

try to download model multiple time but usually stuck on 99% for every .safetensors files, need to cancel and try again multiple time
did someone experience same issue?
also try using Git to clone but with no luck

previously downloading DeepSeekR1 full model only took 6 hours without facing any issue

root@tegpu01worker02:/models# HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 --local-dir models--Qwen--Qwen3-Coder-480B-A35B-Instruct-FP8
Removing incomplete file 'models--Qwen--Qwen3-Coder-480B-A35B-Instruct-FP8/.cache/huggingface/download/iuz8aHLO6Bg3tPS2nIHTyqxKN8g=.8688e8d26a7ca9e3dbef62a7dae247d85014978d558e91e7bba8d7a611548bc7.incomplete' (hf_transfer=True)
Downloading 'model-00006-of-00049.safetensors' to 'models--Qwen--Qwen3-Coder-480B-A35B-Instruct-FP8/.cache/huggingface/download/iuz8aHLO6Bg3tPS2nIHTyqxKN8g=.8688e8d26a7ca9e3dbef62a7dae247d85014978d558e91e7bba8d7a611548bc7.incomplete'
model-00006-of-00049.safetensors: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10.0G/10.0G [01:25<00:00, 116MB/s]
Download complete. Moving file to models--Qwen--Qwen3-Coder-480B-A35B-Instruct-FP8/model-00006-of-00049.safetensors
Downloading 'model-00007-of-00049.safetensors' to 'models--Qwen--Qwen3-Coder-480B-A35B-Instruct-FP8/.cache/huggingface/download/BS4COEvJKSZFsz-UCd7hwQJLFzI=.5bf602baa71a1e711362e06057dc5b01ce08e11c03bd70596f2fa57b783cf9ba.incomplete'
model-00007-of-00049.safetensors:  99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ | 9.86G/10.0G [06:23<00:01, 90.2MB/s]

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