Qwen3.5-397B-A17B-NVFP4-V2

Model Overview

Description:

The NVIDIA Qwen3.5-397B-A17B NVFP4 V2 model is the quantized version of Alibaba's Qwen3.5-397B-A17B model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Qwen3.5-397B-A17B NVFP4 V2 model is quantized with Model Optimizer.

This model is ready for commercial/non-commercial use. <br>

References

Nvidia Model Optimizer: https://github.com/NVIDIA/Model-Optimizer

License/Terms of Use:

Apache license 2.0

Deployment Geography:

Global <br>

Use Case: <br>

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

Release Date: <br>

Hugging Face 06/29/2026 via https://huggingface.co/nvidia/Qwen3.5-397B-A17B-NVFP4-V2 <br>

Model Architecture:

Architecture Type: Transformers <br> Network Architecture: Qwen3.5-397B-A17B <br> Number of Model Parameters: 397B in total and 17B activated <br>

Input:

Input Type(s): Text, Image, Video <br> Input Format(s): String, Red, Green, Blue (RGB), Video (MP4/WebM) <br> Input Parameters: One-Dimensional (1D), Two-Dimensional (2D), Three-Dimensional (3D) <br> Other Properties Related to Input: Context length up to 262K <br>

Output:

Output Type(s): Text <br> Output Format: String <br> Output Parameters: 1D (One-Dimensional): Sequences <br> Other Properties Related to Output: Context length up to 262K <br>

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. <br>

Software Integration:

Supported Runtime Engine(s): <br>

• SGLang <br>

Supported Hardware Microarchitecture Compatibility: <br>

• NVIDIA Blackwell <br>

Preferred Operating System(s): <br>

• Linux <br>

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 version is NVFP4 2.0 version and is quantized with nvidia-modelopt v0.45.0.dev173+g52f1ccbee <br>

Training and Evaluation Datasets:

Calibration Dataset:

Link: cnn_dailymail, Nemotron-Post-Training-Dataset-v2 <br> Data Collection Method by dataset: Automated. <br> Labeling Method by dataset: Automated. <br> Properties: The cnn_dailymail dataset is an English-language dataset containing just over 300k unique news articles as written by journalists at CNN and the Daily Mail. The Nemotron-Post-Training-Dataset-v2 is a post-training dataset curated by NVIDIA containing multi-turn conversations across diverse topics. <br>

Training Dataset:

Data Modality: Undisclosed <br> Data Collection Method by dataset: Undisclosed <br> Labeling Method by dataset: Undisclosed <br> Properties: Undisclosed<br> Audio Training Data Size: Undisclosed<br> Image Training Data Size: Undisclosed<br> Text Training Data Size: Undisclosed<br> Video Training Data Size: Undisclosed<br> Non-Audio, Image, Text Training Data Size: Undisclosed<br>

Evaluation Dataset:

• Datasets: MMMU Pro, GPQA Diamond, SciCode, AA-LCR, IFBench, Tau2 Bench Telecom <br> ** Data Collection Method by dataset: Hybrid: Automated, Human <br> ** Labeling Method by dataset: Hybrid: Human, Automated <br> ** Properties: We evaluated the model on multimodal reasoning, coding, agentic tool-use, and instruction-following benchmarks: MMMU Pro is the more challenging version of the Massive Multi-discipline Multimodal Understanding benchmark, measuring college-level multimodal reasoning across diverse disciplines with expanded answer choices and a vision-only input setting; GPQA Diamond contains 448 graduate-level multiple-choice questions written by domain experts in biology, physics, and chemistry; SciCode evaluates scientific coding capabilities; AA-LCR (Artificial Analysis Long Context Recall) evaluates a model's ability to accurately retrieve and recall information from long input contexts; IFBench is a benchmark for evaluating instruction-following capabilities across diverse and structured task constraints; Tau2 Bench Telecom evaluates agentic tool-use and policy-adherence capabilities in dual-control telecom customer-service scenarios where the model interacts with a simulated user and external tools to resolve account issues. <br>

Inference:

Acceleration Engine: SGLang <br> Test Hardware: B300 <br>

Post Training Quantization

This model was obtained by quantizing the weights and activations of Qwen3.5-397B-A17B to NVFP4 data type, ready for inference with SGLang. The routed experts are quantized to NVFP4 using MSE based scale setting while the attention and shared experts are quantized to per-tensor FP8 format. Only the weights and activations of the linear operators within transformer blocks are quantized.

Usage

To serve this checkpoint with SGLang, you can start the docker lmsysorg/sglang:v0.5.12.post1-cu130 and run the sample command below:

python3 -m sglang.launch_server --model nvidia/Qwen3.5-397B-A17B-NVFP4 --tensor-parallel-size 4 --quantization modelopt_mixed --disable-radix-cache --trust-remote-code

Tip: add --mamba-ssm-dtype bfloat16 to store the Mamba SSM state in BF16 (default is FP32) for faster decode on Blackwell.

Evaluation

The accuracy benchmark results are presented in the table below:

<table> <tr> <td><strong>Precision</strong> </td> <td><strong>MMMU Pro</strong> </td> <td><strong>GPQA Diamond</strong> </td> <td><strong>SciCode</strong> </td> <td><strong>AA-LCR</strong> </td> <td><strong>IFBench</strong> </td> <td><strong>Tau2 Bench Telecom</strong> </td> </tr> <tr> <td>FP8 </td> <td><strong>0.787</strong> </td> <td><strong>0.872</strong> </td> <td><strong>0.467</strong> </td> <td><strong>0.688</strong> </td> <td><strong>0.761</strong> </td> <td><strong>0.954</strong> </td> </tr> <tr> <td>NVFP4 V2 </td> <td><strong>0.784</strong> </td> <td><strong>0.877</strong> </td> <td><strong>0.481</strong> </td> <td><strong>0.678</strong> </td> <td><strong>0.765</strong> </td> <td><strong>0.952</strong> </td> </tr> </table>

Baseline: Qwen3.5-397B-A17B-FP8. Benchmarked with temperature=0.6, top_p=0.95, max num tokens 64000. For tau2 bench telecom we use max num tokens 128000

Model Limitations:

The base model was trained on data that contains toxic language and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.

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.

For more detailed information on ethical considerations for this model, please see the Model Card++ Bias, Explainability, Safety & Security, and Privacy Subcards.

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

SUBCARDS:

Explainability

Bias

Safety & Security

Privacy