Instructions to use Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound with Transformers:

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

pipe = pipeline("text-generation", model="Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound")
model = AutoModelForCausalLM.from_pretrained("Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound", device_map="auto")
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 Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound

SGLang

How to use Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound 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 "Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound" \
    --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": "Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound",
		"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 "Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound" \
        --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": "Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound with Docker Model Runner:
```
docker model run hf.co/Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound
```

CPU only?

by jujutechnology - opened Sep 15, 2025

Discussion

jujutechnology

Sep 15, 2025

Is it true that this runs on cpu only?

wenhuach

Intel org Sep 17, 2025

•

edited Sep 17, 2025

CPU/CUDA

wenhuach

Intel org Sep 17, 2025

For Intel GPU, please use this one https://huggingface.co/Intel/Qwen3-Next-80B-A3B-Thinking-int4-AutoRound

pers0naluni0n

Sep 18, 2025

Is it possible to pack Qwen3-Next-80B-A3B-Thinking-int4-AutoRound into Openvino format?

Would be the icing on the cake

Haihao

Intel org Sep 18, 2025

Is it possible to pack Qwen3-Next-80B-A3B-Thinking-int4-AutoRound into Openvino format?

Would be the icing on the cake

Suggest adding the support of recognizing the autoround format (see the bottom lines of config.json), which is compatible with GPTQ. Meanwhile, you may consider supporting the mixed precision: MoE Linear INT4, and non-MoE linears INT8. Happy to collaborate to enable AutoRound into OpenVINO!

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