unsloth/GLM-5.3-Flash-GGUF · Hugging Face

来源: https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF

https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF#wip-please-stay-tuned开发中，敬请期待

https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF#read-our-how-to-run-glm-53-flash-guide阅读我们的GLM-5.3-Flash运行指南！ (https://unsloth.ai/docs/models/glm-5.3)

Unsloth动态3.0 (https://unsloth.ai/docs/basics/dynamic-3.0-ggufs) 可实现卓越精度并超越其他领先的量化方案。

👋 加入我们的微信 (https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/wechat.png) 或 Discord (https://discord.gg/QR7SARHRxK) 社区。 📖 查看GLM-5.3-Flash博客 (https://z.ai/blog/glm-5.3-flash) 和GLM-5技术报告 (https://arxiv.org/abs/2602.15763)。 📍 在Z.ai API平台上使用GLM-5.3-Flash API服务。 (https://docs.z.ai/guides/llm/glm-5.3-flash)

https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF#introduction简介

我们推出GLM-5.3-Flash，这是GLM-5系列中首个原生多模态模型。它拥有总计320B参数，其中仅18B为活跃参数，以十分之一的成本在各项基准测试和实际工作负载中超越了GLM-5.2，并在编码和智能体基准测试中接近Claude Opus 4.8。

GLM-5.3-Flash从一个新训练的基础模型开始，其架构和训练方案围绕能力和效率重新设计。在GLM系列中，我们首次引入了结合稀疏注意力和线性注意力的混合架构，在保持精确长上下文能力的同时，显著降低了长上下文服务成本。该模型还采用了流形约束超连接（mHC）以进一步提升缩放效率。结合我们最新的30T token多模态预训练语料库，这些改进使得GLM-5.3-Flash能以更少的计算资源提供更强的智能。

bench_53 (https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/bench_53.png)

https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF#footnotes注释

• HLE w/ tools (完整集): 我们使用采样参数temperature=1\.0和top\_p=0\.95进行评估，最大生成长度为16,3840 tokens。评估在最大上下文长度300,000 tokens下进行，使用上下文管理策略。我们使用GPT-5.6-luna (中等) 作为判断模型。
• NL2Repo: 我们在1M上下文下使用temperature=1.0，top_p=1.0，和max_new_tokens=64k评估NL2Repo。为防止滥用，我们使用基于规则和基于LLM的判断来防止恶意行为（例如，未经授权的pip或curl操作）。
• DeepSWE: 我们使用mini-swe-agent工具运行DeepSWE，设置temperature=0\.95、top\_p=1\.0、timeout=6h和400K上下文。
• Terminal-Bench 2.1: 我们在Claude Code 2.1.207中评估，使用temperature=1.0，top_p=1，max_new_tokens=65536，超时时间为6小时。
• Agent’s Last Exam:
• Toolathlon Verified: 我们通过官方评估服务获取所有结果，并报告3次独立运行平均的pass@1。
• AutomationBench: 我们在AutomationBench v1.0.6 上进行评估，包含了PR #13 (https://github.com/zapier/AutomationBench/pull/13) 引入的null类型处理问题的修复。
• GDPval-AA v2: 模型由Artificial Analysis进行评估。
• BabyVision: 我们使用temperature=1.0，top_p=0.95，最大上下文长度164K tokens。我们调整输入图像大小，使其短边至少为1.5K像素，与其他基准保持一致。

https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF#citation引用

如果您在研究中发现GLM-5.3-Flash有用，请引用我们的技术报告：

@misc{glm5team2026glm5vibecodingagentic, title={GLM-5: from Vibe Coding to Agentic Engineering}, author={GLM-5-Team and : and Aohan Zeng and Xin Lv and Zhenyu Hou and Zhengxiao Du and Qinkai Zheng and Bin Chen and Da Yin and Chendi Ge and Chenghua Huang and Chengxing Xie and Chenzheng Zhu and Congfeng Yin and Cunxiang Wang and Gengzheng Pan and Hao Zeng and Haoke Zhang and Haoran Wang and Huilong Chen and Jiajie Zhang and Jian Jiao and Jiaqi Guo and Jingsen Wang and Jingzhao Du and Jinzhu Wu and Kedong Wang and Lei Li and Lin Fan and Lucen Zhong and Mingdao Liu and Mingming Zhao and Pengfan Du and Qian Dong and Rui Lu and Shuang-Li and Shulin Cao and Song Liu and Ting Jiang and Xiaodong Chen and Xiaohan Zhang and Xuancheng Huang and Xuezhen Dong and Yabo Xu and Yao Wei and Yifan An and Yilin Niu and Yitong Zhu and Yuanhao Wen and Yukuo Cen and Yushi Bai and Zhongpei Qiao and Zihan Wang and Zikang Wang and Zilin Zhu and Ziqiang Liu and Zixuan Li and Bojie Wang and Bosi Wen and Can Huang and Changpeng Cai and Chao Yu and Chen Li and Chengwei Hu and Chenhui Zhang and Dan Zhang and Daoyan Lin and Dayong Yang and Di Wang and Ding Ai and Erle Zhu and Fangzhou Yi and Feiyu Chen and Guohong Wen and Hailong Sun and Haisha Zhao and Haiyi Hu and Hanchen Zhang and Hanrui Liu and Hanyu Zhang and Hao Peng and Hao Tai and Haobo Zhang and He Liu and Hongwei Wang and Hongxi Yan and Hongyu Ge and Huan Liu and Huanpeng Chu and Jia'ni Zhao and Jiachen Wang and Jiajing Zhao and Jiamin Ren and Jiapeng Wang and Jiaxin Zhang and Jiayi Gui and Jiayue Zhao and Jijie Li and Jing An and Jing Li and Jingwei Yuan and Jinhua Du and Jinxin Liu and Junkai Zhi and Junwen Duan and Kaiyue Zhou and Kangjian Wei and Ke Wang and Keyun Luo and Laiqiang Zhang and Leigang Sha and Liang Xu and Lindong Wu and Lintao Ding and Lu Chen and Minghao Li and Nianyi Lin and Pan Ta and Qiang Zou and Rongjun Song and Ruiqi Yang and Shangqing Tu and Shangtong Yang and Shaoxiang Wu and Shengyan Zhang and Shijie Li and Shuang Li and Shuyi Fan and Wei Qin and Wei Tian and Weining Zhang and Wenbo Yu and Wenjie Liang and Xiang Kuang and Xiangmeng Cheng and Xiangyang Li and Xiaoquan Yan and Xiaowei Hu and Xiaoying Ling and Xing Fan and Xingye Xia and Xinyuan Zhang and Xinze Zhang and Xirui Pan and Xu Zou and Xunkai Zhang and Yadi Liu and Yandong Wu and Yanfu Li and Yidong Wang and Yifan Zhu and Yijun Tan and Yilin Zhou and Yiming Pan and Ying Zhang and Yinpei Su and Yipeng Geng and Yong Yan and Yonglin Tan and Yuean Bi and Yuhan Shen and Yuhao Yang and Yujiang Li and Yunan Liu and Yunqing Wang and Yuntao Li and Yurong Wu and Yutao Zhang and Yuxi Duan and Yuxuan Zhang and Zezhen Liu and Zhengtao Jiang and Zhenhe Yan and Zheyu Zhang and Zhixiang Wei and Zhuo Chen and Zhuoer Feng and Zijun Yao and Ziwei Chai and Ziyuan Wang and Zuzhou Zhang and Bin Xu and Minlie Huang and Hongning Wang and Juanzi Li and Yuxiao Dong and Jie Tang}, year={2026}, eprint={2602.15763}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2602.15763}, }

unsloth/GLM-5.3-Flash-GGUF的模型树https://huggingface.co/docs/hub/model-cards#specifying-a-base-model

unsloth/GLM-5.3-Flash-GGUF的论文