GLM-4.7-Flash-GPTQ-4bit

FayeQuant/GLM-4.7-Flash-GPTQ-4bit

Description

This repo contains GPTQ model files for zai-org/GLM-4.7-Flash.

Performances on Benchmarks

Known Issue

1. Unable to run with vllm on V100 (SM 7.0)

(Pending PR into upstream). https://github.com/FayeSpica/vllm/tree/glm_flash_fix

Serve GLM-4.7-Flash Locally

For local deployment, GLM-4.7-Flash supports inference frameworks including vLLM and SGLang. Comprehensive deployment instructions are available in the official Github repository.

vLLM and SGLang only support GLM-4.7-Flash on their main branches.

vLLM(V100 Only)

• using pip:

pip install git+https://github.com/FayeSpica/vllm.git@glm_flash_fix
pip install transformers==5.1.0

Can not use mtp

vllm serve FayeQuant/GLM-4.7-Flash-GPTQ-4bit \
     --max-model-len auto \
     --tool-call-parser glm47 \
     --reasoning-parser glm45 \
     --enable-auto-tool-choice \
     --served-model-name glm-4.7-flash

V100 Benchmarks

Concurrency 1:

============ Serving Benchmark Result ============
Successful requests:                     8         
Failed requests:                         0         
Maximum request concurrency:             1         
Benchmark duration (s):                  105.03    
Total input tokens:                      8192      
Total generated tokens:                  1024      
Request throughput (req/s):              0.08      
Output token throughput (tok/s):         9.75      
Peak output token throughput (tok/s):    11.00     
Peak concurrent requests:                2.00      
Total token throughput (tok/s):          87.75     
---------------Time to First Token----------------
Mean TTFT (ms):                          395.51    
Median TTFT (ms):                        384.78    
P99 TTFT (ms):                           468.10    
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          100.26    
Median TPOT (ms):                        100.17    
P99 TPOT (ms):                           101.30    
---------------Inter-token Latency----------------
Mean ITL (ms):                           100.26    
Median ITL (ms):                         100.55    
P99 ITL (ms):                            111.62    
==================================================

Concurrency 6:

============ Serving Benchmark Result ============
Successful requests:                     48        
Failed requests:                         0         
Maximum request concurrency:             6         
Benchmark duration (s):                  153.73    
Total input tokens:                      49152     
Total generated tokens:                  6144      
Request throughput (req/s):              0.31      
Output token throughput (tok/s):         39.97     
Peak output token throughput (tok/s):    54.00     
Peak concurrent requests:                12.00     
Total token throughput (tok/s):          359.69    
---------------Time to First Token----------------
Mean TTFT (ms):                          1964.40   
Median TTFT (ms):                        1979.09   
P99 TTFT (ms):                           2038.77   
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          135.82    
Median TPOT (ms):                        137.50    
P99 TPOT (ms):                           139.47    
---------------Inter-token Latency----------------
Mean ITL (ms):                           135.82    
Median ITL (ms):                         137.60    
P99 ITL (ms):                            147.23    
==================================================

vLLM

• using pip:

pip install vllm>=0.15.0
pip install transformers>=5.1.0

vllm serve FayeQuant/GLM-4.7-Flash-GPTQ-4bit \
     --max-model-len auto \
     --speculative-config.method mtp \
     --speculative-config.num_speculative_tokens 1 \
     --tool-call-parser glm47 \
     --reasoning-parser glm45 \
     --enable-auto-tool-choice \
     --served-model-name glm-4.7-flash

GLM-4.7-Flash

<div align="center"> <img src=https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/logo.svg width="15%"/> </div> <p align="center"> 👋 Join our <a href="https://discord.gg/QR7SARHRxK" target="_blank">Discord</a> community. <br> 📖 Check out the GLM-4.7 <a href="https://z.ai/blog/glm-4.7" target="_blank">technical blog</a>, <a href="https://arxiv.org/abs/2508.06471" target="_blank">technical report(GLM-4.5)</a>. <br> 📍 Use GLM-4.7-Flash API services on <a href="https://docs.z.ai/guides/llm/glm-4.7">Z.ai API Platform. </a> <br> 👉 One click to <a href="https://chat.z.ai">GLM-4.7</a>. </p>

Introduction

GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

Performances on Benchmarks

Evaluation Parameters

Default Settings (Most Tasks)

• temperature: 1.0
• top-p: 0.95
• max new tokens: 131072

For multi-turn agentic tasks (τ²-Bench and Terminal Bench 2), please turn on Preserved Thinking mode.

Terminal Bench, SWE Bench Verified

• temperature: 0.7
• top-p: 1.0
• max new tokens: 16384

τ^2-Bench

• Temperature: 0
• Max new tokens: 16384

For τ^2-Bench evaluation, we added an additional prompt to the Retail and Telecom user interaction to avoid failure modes caused by users ending the interaction incorrectly. For the Airline domain, we applied the domain fixes as proposed in the Claude Opus 4.5 release report.

Citation

If you find our work useful in your research, please consider citing the following paper:

@misc{5team2025glm45agenticreasoningcoding,
      title={GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models}, 
      author={GLM Team and Aohan Zeng and Xin Lv and Qinkai Zheng and Zhenyu Hou and Bin Chen and Chengxing Xie and Cunxiang Wang and Da Yin and Hao Zeng and Jiajie Zhang and Kedong Wang and Lucen Zhong and Mingdao Liu and Rui Lu and Shulin Cao and Xiaohan Zhang and Xuancheng Huang and Yao Wei and Yean Cheng and Yifan An and Yilin Niu and Yuanhao Wen and Yushi Bai and Zhengxiao Du and Zihan Wang and Zilin Zhu and Bohan Zhang and Bosi Wen and Bowen Wu and Bowen Xu and Can Huang and Casey Zhao and Changpeng Cai and Chao Yu and Chen Li and Chendi Ge and Chenghua Huang and Chenhui Zhang and Chenxi Xu and Chenzheng Zhu and Chuang Li and Congfeng Yin and Daoyan Lin and Dayong Yang and Dazhi Jiang and Ding Ai and Erle Zhu and Fei Wang and Gengzheng Pan and Guo Wang and Hailong Sun and Haitao Li and Haiyang Li and Haiyi Hu and Hanyu Zhang and Hao Peng and Hao Tai and Haoke Zhang and Haoran Wang and Haoyu Yang and He Liu and He Zhao and Hongwei Liu and Hongxi Yan and Huan Liu and Huilong Chen and Ji Li and Jiajing Zhao and Jiamin Ren and Jian Jiao and Jiani Zhao and Jianyang Yan and Jiaqi Wang and Jiayi Gui and Jiayue Zhao and Jie Liu and Jijie Li and Jing Li and Jing Lu and Jingsen Wang and Jingwei Yuan and Jingxuan Li and Jingzhao Du and Jinhua Du and Jinxin Liu and Junkai Zhi and Junli Gao and Ke Wang and Lekang Yang and Liang Xu and Lin Fan and Lindong Wu and Lintao Ding and Lu Wang and Man Zhang and Minghao Li and Minghuan Xu and Mingming Zhao and Mingshu Zhai and Pengfan Du and Qian Dong and Shangde Lei and Shangqing Tu and Shangtong Yang and Shaoyou Lu and Shijie Li and Shuang Li and Shuang-Li and Shuxun Yang and Sibo Yi and Tianshu Yu and Wei Tian and Weihan Wang and Wenbo Yu and Weng Lam Tam and Wenjie Liang and Wentao Liu and Xiao Wang and Xiaohan Jia and Xiaotao Gu and Xiaoying Ling and Xin Wang and Xing Fan and Xingru Pan and Xinyuan Zhang and Xinze Zhang and Xiuqing Fu and Xunkai Zhang and Yabo Xu and Yandong Wu and Yida Lu and Yidong Wang and Yilin Zhou and Yiming Pan and Ying Zhang and Yingli Wang and Yingru Li and Yinpei Su and Yipeng Geng and Yitong Zhu and Yongkun Yang and Yuhang Li and Yuhao Wu and Yujiang Li and Yunan Liu and Yunqing Wang and Yuntao Li and Yuxuan Zhang and Zezhen Liu and Zhen Yang and Zhengda Zhou and Zhongpei Qiao and Zhuoer Feng and Zhuorui Liu and Zichen Zhang and Zihan Wang and Zijun Yao and Zikang Wang and Ziqiang Liu and Ziwei Chai and Zixuan Li and Zuodong Zhao and Wenguang Chen and Jidong Zhai and Bin Xu and Minlie Huang and Hongning Wang and Juanzi Li and Yuxiao Dong and Jie Tang},
      year={2025},
      eprint={2508.06471},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.06471}, 
}