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

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
```

GGUF when? 8 bit quant when?

by ouchiewouchie - opened Sep 11, 2025

Discussion

ouchiewouchie

Sep 11, 2025

Just a little system prompt bro, need to see it's math capability ask it about how many r's in strawberry c'mon bro, pls man, just a little test

victor

Sep 11, 2025

should drop very soon it's in community hands now 🚀

shihab456321

Sep 11, 2025

when the q8 gguf will come?

jtdavies

Sep 12, 2025

I just tried to GGUF the 162.68 GB HF model and it seems it's not supported yet in Llama.cpp. I tried making a few changes but it's 3am in Europe and I'm off to sleep, sadly without being able to test the model. without Llama.cpp then none of the other tools like Ollama, LM Studio etc. are going to have support. I'm sure it won't be long, hopefully by the time I wake up :-)