Instructions to use Qwen/Qwen3-Next-80B-A3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3-Next-80B-A3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen3-Next-80B-A3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Next-80B-A3B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Next-80B-A3B-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-Next-80B-A3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3-Next-80B-A3B-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-Next-80B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3-Next-80B-A3B-Instruct

SGLang

How to use Qwen/Qwen3-Next-80B-A3B-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-Next-80B-A3B-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-Next-80B-A3B-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-Next-80B-A3B-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-Next-80B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen3-Next-80B-A3B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3-Next-80B-A3B-Instruct
```

Will smaller Qwen3-Next models be released in the future?

#15

by ZAID041 - opened Sep 12, 2025

Discussion

ZAID041

Sep 12, 2025

Hi, and thanks for sharing the new Qwen3-Next-80B-A3B-Instruct model — it looks really impressive.

Since this release is very new (just announced recently), I was wondering:
-Do you plan to release smaller Qwen3-Next variants (e.g., 7B, 14B, 32B) with the same architecture in the near future?

This would be very useful for researchers and developers who don’t have access to the compute needed for 80B models but still want to benefit from the new Hybrid Attention + MoE + MTP architecture.

Thanks!

melekuk

Sep 13, 2025

this architecture is a preview for the next release https://x.com/JustinLin610/status/1966199996728156167

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