Qwen3-Next-80B-A3B-Instruct-4bit-SINQ

<p align="center"> <img src="logo.png" alt="Logo" style="max-width: 80%; height: auto;"> </p> <p align="center">🐙 <a href="https://github.com/huawei-csl/SINQ">Github</a>&nbsp;&nbsp; | &nbsp;&nbsp;📄 <a href="http://arxiv.org/abs/2509.22944">Paper</a></p>

SINQ 4-bit Quantized Qwen3-Next 80B model

This repository contains the official 4-bit quantized version of the Qwen3-Next-80B model using the SINQ (Sinkhorn-Normalized Quantization) method.
SINQ is a novel, fast and high-quality quantization method designed to make any Large Language Models smaller while keeping their accuracy almost intact.

To support the project please put a star ⭐ in the official SINQ github repository.

Model Details

• Model Name: Qwen3-Next-80B-A3B-Instruct-4bit-SINQ
• Base Model: Qwen3-Next-80B
• Task: Text Generation
• Framework: PyTorch / Transformers
• License: Apache-2.0
• Quantized By: Huawei - Computing Systems Lab

Quantization Details

• Quantization Method: SINQ (Sinkhorn-Normalized Quantization)
• Precision: INT4
• Group Size: 64
• Framework: PyTorch
• Quantization Library: sinq

---

🚀 Usage

Prerequisite

Before running the quantization script, make sure the SINQ library is installed. Installation instructions and setup details are available in the SINQ official github repository.

Usage example

You can load and use the model with our wrapper based on the 🤗 Transformers library:

import torch
from transformers import AutoTokenizer
from sinq.patch_model import AutoSINQHFModel

model_name = "huawei-csl/Qwen3-Next-80B-A3B-Instruct-4bit-SINQ"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sinq_model = AutoSINQHFModel.from_quantized_safetensors(
    model_name,
    device="cuda:0",
    compute_dtype=torch.bfloat16
)

# prepare the model input
prompt = "Explain neural network quantization in one sentence."
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(sinq_model.device)
    
# conduct text completion
generated_ids = sinq_model.generate(
    **model_inputs,
    temperature=0.7,
    top_p=0.8,
    top_k=20,
    min_p=0.0,
    max_new_tokens=16384,
)

output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

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

print("content:", content)

<details> <summary><span style="font-size:1.1em; font-weight:bold;">🧩 Quantization Process</span></summary>

The quantized model was obtained using the SINQ quantization library, following the steps below:

from transformers import AutoModelForCausalLM, AutoTokenizer
from sinq.patch_model import AutoSINQHFModel
from sinq.sinqlinear import BaseQuantizeConfig

# Load base model
base_model_name = "Qwen/Qwen3-Next-80B-A3B-Instruct"
model = AutoModelForCausalLM.from_pretrained(base_model_name, torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(base_model_name)

# Apply 4-bit SINQ quantization
quant_cfg = BaseQuantizeConfig(
    nbits=4,            # quantization bit-width
    group_size=64,     # group size
    tiling_mode="1D",   # tiling strategy
    method="sinq"       # quantization method ("asinq" for the calibrated version)
)

sinq_model = AutoSINQHFModel.quantize_model(
    model,
    tokenizer=tokenizer,
    quant_config=quant_cfg,
    compute_dtype=torch.bfloat16,
    device="cuda:0"
)

Reproducibility Note: This model was quantized using the SINQ implementation from commit ee1dc76 of the SINQ repository.

</details> </br>

---

🧾 How to Cite This Work

If you find SINQ useful in your research or applications, please

• Put a star ⭐ in the official SINQ github repository.
• Cite our <a href="http://arxiv.org/abs/2509.22944" target="_blank"><strong>paper</strong></a>:

@misc{muller2025sinq,
      title={SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights}, 
      author={Lorenz K. Muller and Philippe Bich and Jiawei Zhuang and Ahmet Celik and Luca Benfenati and Lukas Cavigelli},
      year={2025},
      eprint={2509.22944},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={http://arxiv.org/abs/2509.22944}
}