Cataloged from nvidia/Qwen3-8B-NVFP4
The NVIDIA Qwen3-8B FP4 model is the quantized version of Alibaba's Qwen3-8B model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Qwen3-8B FP4 model is quantized with TensorRT Model Optimizer.
This model is ready for commercial/non-commercial use.
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 (Qwen3-8B) Model Card.
Use of this model is governed by Apache license 2.0
Global
Developers looking to take off the shelf pre-quantized models for deployment in AI Agent systems, chatbots, RAG systems, and other AI-powered applications.
Huggingface 09/15/2025 via https://huggingface.co/nvidia/Qwen3-8B-FP4
Architecture Type: Transformers Network Architecture: Qwen3-8B
**This model was developed based on Qwen3-8B **Number of model parameters: 8.2*10^9
Input Type(s): Text Input Format(s): String Input Parameters: 1D (One-Dimensional): Sequences Other Properties Related to Input: Context length up to 131K
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.
Supported Runtime Engine(s):
Supported Hardware Microarchitecture Compatibility:
Preferred Operating System(s):
The model is quantized with nvidia-modelopt v0.35.0
This model was obtained by quantizing the weights and activations of Qwen3-8B to FP4 data type, ready for inference with TensorRT-LLM. Only the weights and activations of the linear operators within transformer blocks are quantized.
** Data Modality
** Link: cnn_dailymail ** Data collection method: Automated. ** Labeling method: Automated.
** Data Collection Method by Dataset: Undisclosed ** Labeling Method by Dataset: Undisclosed ** Properties: Undisclosed
** Data Collection Method by Dataset: Undisclosed ** Labeling Method by Dataset: Undisclosed ** Properties: Undisclosed
Engine: TensorRT-LLM Test Hardware: B200
To deploy the quantized checkpoint with TensorRT-LLM LLM API, follow the sample codes below:
from tensorrt_llm import LLM, SamplingParams
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=0.8, top_p=0.95)
llm = LLM(model="nvidia/Qwen3-8B-FP4")
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()
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.