---

license: mit

---

easiest-ai-shawn/GLM-5.2-IQMax-320GB-Final-GGUF

It is my pleasure to present to you my final quantization of GLM 5.2 🥲

This variant was originally codenamed siq19 as it was the 19th series-unique quantization effort to make a high quality Special/Small I-Quant.

attn_k_b tensors are quantized to q8_0 for best effort to avoid f16 overhead while being divisible by 256.

The remaining attention tensors are quantized to q6_k to avoid performance issues related to q8 quants (see issue #24002).

See ./quantization_logs.txt for a complete breakdown of all tensors, layers, and individual sizes.

This quant moniker is a combination of being my personal favorite within my series and my parting ways with hardware to cover expenses.

While I will no longer be able to run this quant in the near term, it is my hope others may enjoy the fruits of my efforts.

Download

hf download easiest-ai-shawn/GLM-5.2-IQMax-320GB-Final-GGUF --local-dir ./easiest-ai-shawn/GLM-5.2-IQMax-320GB-Final-GGUF

Example Params

Note: Very strict sampling, for rigid precision; same as used for SVG examples. You may wish to use a higher temperature and 2-4k reasoning budget.

./build/bin/llama-server \
  -m ./easiest-ai-shawn/GLM-5.2-IQMax-320GB-Final-GGUF \
  --fit 1 -fitt 1024 \
  --no-mmap \
  --mlock \
  -c 128000 \
  --reasoning-budget 500 \
  --reasoning-budget-message " ... thinking limit exceeded." \
  --samplers "top_k;penalties;temperature" \
  --temp 0.28 \
  --top-k 29 \
  --top-p 1.0 \
  --min-p 0.21 \
  -ctk q8_0 -ctv q8_0 \
  -kvu -fa 1 \
  -b 2048 -ub 2048 \
  --no-warmup

Support my work and help me rebuild my rig:

- Patreon

- Ko-Fi

Catbench (inspired by ExllamaV3 community), at low temperatures:

> "create an SVG of a cute kitten"

!cute-kitten_1.svg

> "create an SVG of a cute kitten"

!cute-kitten_2.svg

> "create a highly detailed SVG of a cute kitten"

!kitten_highly-detailed.svg

Base model: https://huggingface.co/zai-org/GLM-5.2

Recipe: ./tensor_types.txt

Quantization Logs: ./quantization_logs.txt

Quantized against customized imatrix:

- unsloth 1000 chunk base https://huggingface.co/unsloth/GLM-5.2-GGUF/blob/main/imatrix_unsloth.gguf_file

- 2000 appended custom chunks

- easiest.ai proprietary dense planning, code, and world reference data.

- https://huggingface.co/datasets/AI-MO/NuminaMath-1.5

- https://huggingface.co/datasets/amphora/ResearchMath-14k

- https://huggingface.co/datasets/qwedsacf/competition_math

- https://huggingface.co/datasets/fka/prompts.chat

- https://huggingface.co/datasets/SWE-bench/SWE-bench_Verified

---

MIT License

Modifications Copyright 2026 easiest.ai All rights reserved.

@misc{GLM-5.2-IQMax-320GB-Final-GGUF,
  title={easiest-ai-shawn/GLM-5.2-IQMax-320GB-Final-GGUF},
  author={easiest-ai-shawn},
  year={2026},
}

GLM 5.2 Base Model:

@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},
}

GLM 5.1 Draft Model:

@misc{glm5.1eagle3,
  title={GLM-5.1-eagle3: Accelerating Instruction Following with EAGLE3},
  author={Ant AQ Team},
  year={2026},
}

GLM 5.2 I-Matrix Base:

MIT License

https://huggingface.co/unsloth/GLM-5.2-GGUF/blob/main/imatrix_unsloth.gguf_file

NuminaMath:

@misc{numina_math_datasets,
  author = {Jia LI and Edward Beeching and Lewis Tunstall and Ben Lipkin and Roman Soletskyi and Shengyi Costa Huang and Kashif Rasul and Longhui Yu and Albert Jiang and Ziju Shen and Zihan Qin and Bin Dong and Li Zhou and Yann Fleureau and Guillaume Lample and Stanislas Polu},
  title = {NuminaMath},
  year = {2024},
  publisher = {Numina},
  journal = {Hugging Face repository},
  howpublished = {\url{[https://huggingface.co/datasets/AI-MO/NuminaMath-1.5](https://github.com/project-numina/aimo-progress-prize/blob/main/report/numina_dataset.pdf)}}
}

ResearchMath:

@article{son2026researchmath,
  title={ResearchMath-14K: Scaling Research-Level Mathematics via Agents},
  author={Son, Guijin and Yi, Seungyeop and Gwak, Minju and Ko, Hyunwoo and Jang, Wongi and Yu, Youngjae},
  journal={arXiv preprint arXiv:2605.28003},
  year={2026}
}

Competition Math:

@article{hendrycksmath2021,
    title={Measuring Mathematical Problem Solving With the MATH Dataset},
    author={Dan Hendrycks
    and Collin Burns
    and Saurav Kadavath
    and Akul Arora
    and Steven Basart
    and Eric Tang
    and Dawn Song
    and Jacob Steinhardt},
    journal={arXiv preprint arXiv:2103.03874},
    year={2021}
}

Prompt Chat:

CC0 1.0 Universal (Public Domain Dedication)

https://huggingface.co/datasets/fka/prompts.chat

SWE Bench Verified:

MIT License

https://huggingface.co/datasets/SWE-bench/SWE-bench_Verified