nvidia/Qwen3-Next-80B-A3B-Thinking-NVFP4

Model Overview

Description:

The NVIDIA Qwen3-Next-80B-A3B-Thinking NVFP4 model is the quantized version of Alibaba's Qwen3-Next-80B-A3B-Thinking model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Qwen3-Next-80B-A3B-Thinking NVFP4 model is quantized with TensorRT Model Optimizer.

This model is ready for commercial/non-commercial use.

Third-Party Community Consideration

This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA (Qwen3-Next-80B-A3B-Thinking) Model Card.

License/Terms of Use:

Apache license 2.0

Deployment Geography:

Global

Use Case:

Developers looking to take off the shelf pre-quantized models for deployment in AI Agent systems, chatbots, RAG systems, and other AI-powered applications.

Release Date:

Huggingface 12/29/2025 via https://huggingface.co/nvidia/Qwen3-Next-80B-A3B-Thinking-NVFP4

Model Architecture:

Architecture Type: Transformers
Network Architecture: Qwen3NextForCausalLM
**This model was developed based on Qwen3-Next-80B-A3B-Thinking
**Number of model parameters: Undisclosed.

Input:

Input Type(s): Text
Input Format(s): String
Input Parameters: 1D (One-Dimensional): Sequences
Other Properties Related to Input: Context length 262,144 natively and extensible up to 1,010,000 tokens

Output:

Output Type(s): Text
Output Format: String
Output Parameters: 1D (One-Dimensional): Sequences
Other Properties Related to Output: N/A

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Software Integration:

Runtime Engine(s):

• TensorRT-LLM
  

Supported Hardware Microarchitecture Compatibility:

• NVIDIA Blackwell
  

Preferred Operating System(s):

• Linux
  

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment

Model Version(s):

The model is quantized with nvidia-modelopt v0.40.0

Training, Testing, and Evaluation Datasets:

Calibration Dataset:

** Link: cnn_dailymail, Nemotron-Post-Training-Dataset-v2
** Data collection method: Automated.
** Labeling method: Automated.

Training Datasets:

** Data Collection Method by Dataset: Undisclosed
** Labeling Method by Dataset: Undisclosed
** Properties: Undisclosed

Testing Dataset:

** Data Collection Method by Dataset: Undisclosed
** Labeling Method by Dataset: Undisclosed
** Properties: Undisclosed

Evaluation Dataset:

• Datasets: MMLU Pro, GPQA Diamond, LiveCodeBench V6, SciCode, AIME 2025
  ** Data collection method: Hybrid: Automated, Human
  ** Labeling method: Hybrid: Human, Automated
  

Inference:

Acceleration Engine: TensorRT-LLM
Test Hardware: B200

Post Training Quantization

This model was obtained by quantizing the weights and activations of Qwen3-Next-80B-A3B-Thinking to NVFP4 data type, ready for inference with TensorRT-LLM. Only the weights and activations of the linear operators within transformer blocks are quantized. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 3.3x.

Usage

Deploy with TensorRT-LLM

To deploy the quantized checkpoint with TensorRT-LLM LLM API, follow the sample codes below:

• LLM API sample usage:

from tensorrt_llm import LLM, SamplingParams, KvCacheConfig


def main():

    prompts = [
        "Hello, my name is",
        "The president of the United States is",
        "The capital of France is",
        "The future of AI is",
    ]
    sampling_params = SamplingParams(temperature=0.6, top_p=0.95)
    kv_cache_config = KvCacheConfig(enable_block_reuse=False)

    llm = LLM(model="nvidia/Qwen3-Next-80B-A3B-Thinking-NVFP4", tensor_parallel_size=4, kv_cache_config=kv_cache_config)

    outputs = llm.generate(prompts, sampling_params)

    # Print the outputs.
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")


# The entry point of the program needs to be protected for spawning processes.
if __name__ == '__main__':
    main()

Evaluation

The accuracy benchmark results are presented in the table below:

Precision	MMLU Pro	GPQA Diamond	LiveCodeBench V6	SciCode	AIME 2025
FP8	0.823	0.754	0.714	0.414	0.879
NVFP4	0.822	0.752	0.708	0.409	0.862

Baseline: Qwen3-Next-80B-A3B-Thinking-FP8. Benchmarked with temperature=0.6, top_p=0.95, max num tokens 81920

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.