metadata

license: apache-2.0
license_link: https://huggingface.co/Qwen/QWQ-32B-GGUF/blob/main/LICENSE
language:
  - en
pipeline_tag: text-generation
base_model: Qwen/QwQ-32B
tags:
  - chat

QwQ-32B-GGUF

Introduction

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 repo contains the QwQ 32B model in the GGUF Format, which has the following features:

Type: Causal Language Models
Training Stage: Pretraining & Post-training (Supervised Finetuning and Reinforcement Learning)
Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Number of Parameters: 32.5B
Number of Paramaters (Non-Embedding): 31.0B
Number of Layers: 64
Number of Attention Heads (GQA): 40 for Q and 8 for KV
Context Length: Full 131,072 tokens
Quantization: q2_K, q3_K_M, q4_0, q4_K_M, q5_0, q5_K_M, q6_K, q8_0

Note: For the best experience, please review the usage guidelines before deploying QwQ models.

You can try our demo or access QwQ models via QwenChat.

For more details, please refer to our blog, GitHub, and Documentation.

Requirements

QwQ is based on Qwen2.5, whose code has been in the latest Hugging face transformers. We advise you to use the latest version of transformers.

With transformers<4.37.0, you will encounter the following error:

KeyError: 'qwen2'

Also check out our AWQ documentation for more usage guide.

Quickstart

heck out our llama.cpp documentation for more usage guide.

We advise you to clone llama.cpp and install it following the official guide. We follow the latest version of llama.cpp. In the following demonstration, we assume that you are running commands under the repository llama.cpp.

Since cloning the entire repo may be inefficient, you can manually download the GGUF file that you need or use huggingface-cli:

Install
```
pip install -U huggingface_hub
```
Download:
```
huggingface-cli download Qwen/QwQ-32B-GGUF --include "qwq-32b-q5_k_m*.gguf" --local-dir . --local-dir-use-symlinks False
```
For large files, we split them into multiple segments due to the limitation of file upload. They share a prefix, with a suffix indicating its index. For examples, qwq-32b-q5_k_m-00001-of-00006.gguf, qwq-32b-q5_k_m-00002-of-00006.gguf, ... and qwq-32b-q5_k_m-00006-of-00006.gguf. The above command will download all of them.

(Optional) Merge: For split files, you need to merge them first with the command llama-gguf-split as shown below:

# ./llama-gguf-split --merge <first-split-file-path> <merged-file-path>
./llama-gguf-split --merge qwq-32b-q5_k_m-00001-of-00006.gguf qwq-32b-q5_k_m.gguf

For users, to achieve chatbot-like experience, it is recommended to commence in the conversation mode:

./llama-cli -m <gguf-file-path>

Usage Guidelines

To achieve optimal performance, we recommend the following settings:

Enforce Thoughtful Output: Ensure the model starts with "<think>\n" to prevent generating empty thinking content, which can degrade output quality.
Sampling Parameters:
- Use Temperature=0.6 and TopP=0.95 instead of Greedy decoding to avoid endless repetitions.
- Use TopK between 20 and 40 to filter out rare token occurrences while maintaining the diversity of the generated output.
No Thinking Content in History: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. This feature is already implemented in apply_chat_template.
Standardize Output Format: We recommend using prompts to standardize model outputs when benchmarking.
- Math Problems: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
- Multiple-Choice Questions: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the answer field with only the choice letter, e.g.,\"answer\": \"C\"." in the prompt.
Handle Long Inputs: For inputs exceeding 32,768 tokens, enable YaRN to improve the model's ability to capture long-sequence information effectively. Currently, only vLLM supports YARN for length extrapolating. If you want to process sequences up to 131,072 tokens, please refer to non-GGUF models.

Evaluation & Performance

Detailed evaluation results are reported in this 📑 blog.

For requirements on GPU memory and the respective throughput, see results here.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwq32b,
    title = {QwQ-32B: The Power of Scaling RL},
    url = {https://qwenlm.github.io/blog/qwq-32b/},
    author = {Qwen Team},
    month = {March},
    year = {2025}
}

@article{qwen2,
      title={Qwen2 Technical Report}, 
      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
      journal={arXiv preprint arXiv:2407.10671},
      year={2024}
}