---
base_model:
- Qwen/Qwen3-Next-80B-A3B-Instruct
pipeline_tag: text-generation
license: apache-2.0
---

## Model Details

This model is a int4 model with group_size 128 and symmetric quantization of [Qwen/Qwen3-Next-80B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct) generated by [intel/auto-round](https://github.com/intel/auto-round).
Please follow the license of the original model.

## How To Use

For vllm, this pr is required https://github.com/vllm-project/vllm/pull/24818

### INT4 Inference
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import transformers
import torch
quantized_model_dir = "Intel/Qwen3-Next-80B-A3B-Instruct-int4-AutoRound"

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

# prepare the model input
prompt = "Give me a short introduction to large language model."
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=512,
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

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

print("content:", content)
"""
content: A large language model (LLM) is a type of artificial intelligence system trained on vast amounts of text data to understand and generate human-like language. These models learn patterns, grammar, context, and reasoning from billions of words, enabling them to answer questions, write essays, translate languages, code, and even engage in conversation. Popular examples include OpenAI’s GPT series, Google’s Gemini, and Meta’s Llama. LLMs are foundational to many modern AI applications, from chatbots to content creation tools, though they require careful use due to potential biases, inaccuracies, and ethical concerns.
"""
```

### vLLM 
The following command can be used to create an API endpoint at `http://localhost:8000/v1` with maximum context length 256K tokens.
```shell
vllm serve Intel/Qwen3-Next-80B-A3B-Instruct-int4-AutoRound --port 8000 --max-model-len 262144
```

The following command is recommended for MTP with the rest settings the same as above:
```shell
vllm serve Intel/Qwen3-Next-80B-A3B-Instruct-int4-AutoRound --port 8000 --max-model-len 262144 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
```

```bash
curl -noproxy '*' http://localhost::8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "messages": [
        {"role": "user", "content": "Give me a short introduction to large language model."}
        ],
        "max_tokens": 1024
    }'

# "content":
#    "A large language model (LLM) is a type of artificial intelligence system trained on vast amounts of text data to understand, generate, and manipulate human language. These models use deep learning architectures—often based on the transformer network—to predict the next word in a sequence, enabling them to perform tasks like answering questions, writing essays, translating languages, and even coding. LLMs, such as GPT, Gemini, and Claude, learn patterns and relationships in language without explicit programming, allowing them to produce human-like responses across a wide range of topics. While powerful, they don’t “understand” language in the human sense and can sometimes generate plausible-sounding but incorrect or biased information.",
```

### Generate the model
```bash
AR_DISABLE_COPY_MTP_WEIGHTS=1 auto_round --model Qwen/Qwen3-Next-80B-A3B-Instruct --scheme W4A16 --output_dir tmp_autoround
```

## Evaluate Results

| benchmark | n-shot | backend | Intel/Qwen3-Next-80B-A3B-Instruct-int4-AutoRound | Qwen/Qwen3-Next-80B-A3B-Instruct |
| :-------: | :----: | :-----: | :----------------------------------------------: | :------------------------------: |
|   gsm8k   |   5    |  vllm   |                      0.8643                      |              0.8074              |
| mmlu_pro  |   5    |  vllm   |                      0.7570                      |              0.7621              |

## Ethical Considerations and Limitations

The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Therefore, before deploying any applications of the model, developers should perform safety testing.

## Caveats and Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Here are a couple of useful links to learn more about Intel's AI software:

- [Intel Neural Compressor](https://github.com/intel/neural-compressor)

## Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

## Cite

@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)