qwq-32b

Model Overview

Description

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

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 QwQ-32B Model Card.

License/Terms of Use

Qwen/QwQ-32B is licensed under the Apache 2.0 License

References:

Blog, Github, Documentation, Technical Report

Model Architecture:

Architecture Type: Transformer with RoPE, SwiGLU, RMSNorm, and Attention QKV bias Network Architecture: Qwen2.5

This model was developed based on Qwen2.5 and has 32.5B of model parameters.

Input:

Input Type(s): Text
Input Format(s): String
Input Parameters: 1D Other Properties Related to Input: Support up to 131,072 tokens

Output:

Output Type(s): Text
Output Format: String
Output Parameters: 1D Other Properties Related to Output: Generate up to 32,768 tokens

Model Version(s):

QwQ-32B

Training, Testing, and Evaluation Datasets:

Training Dataset:

Link: Unknown
Data Collection Method by dataset: Unknown
Labeling Method by dataset: Unknown
Properties: Unknown

Testing Dataset:

Link: Unknown
Data Collection Method by dataset: Unknown
Labeling Method by dataset: Unknown
Properties: Unknown

Evaluation Dataset:

Link: Detailed evaluation results are reported in this blog QwQ-32B: Embracing the Power of Reinforcement Learning
Data Collection Method by dataset: Unknown
Labeling Method by dataset: Unknown
Properties: Unknown

Inference:

Engine: TensorRT-LLM
Test Hardware: NVIDIA L40S

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 security vulnerabilities or NVIDIA AI Concerns here.