aquaduck / GLM-4.7-Flash-GGUF

Model Card for aquaduck/GLM-4.7-Flash-GGUF

Layer-sharded Q4_K_M GGUF chunks of Z.ai GLM-4.7-Flash, derived from unsloth/GLM-4.7-Flash-GGUF.

These files are not a new quantization. They are contiguous 4-layer packages (final chunk is 3 layers) cut from the full Unsloth Q4_K_M GGUF for staged / multi-node loading (Aquaduck Arc layer-package-v1).

Model lineage

zai-org/GLM-4.7-Flash └── quantized → unsloth/GLM-4.7-Flash-GGUF (Q4_K_M) └── layer-split → aquaduck/GLM-4.7-Flash-GGUF (this repo)

• Base weights: https://huggingface.co/zai-org/GLM-4.7-Flash (MIT)
• Quantization source: https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF (tag Q4_K_M)
• This repo: 4-layer GGUF shards for distributed inference

Model Details

Model Description

• Developed by: Aquaduck (layer packaging only; base model by Z.ai / GLM Team; GGUF quant by Unsloth / llama.cpp ecosystem)
• Shared by: Aquaduck AI
• Model type: Causal language model (GLM-4 MoE Lite / 30B-A3B), GGUF Q4_K_M, layer-sharded
• Language(s): Multilingual (same as base; primarily English and Chinese)
• License: MIT (inherits from zai-org/GLM-4.7-Flash)
• Finetuned from model: N/A — not a fine-tune
• Derived from: unsloth/GLM-4.7-Flash-GGUF ← zai-org/GLM-4.7-Flash

Model Sources

• Base model card / paper: https://huggingface.co/zai-org/GLM-4.7-Flash , https://arxiv.org/abs/2508.06471
• Quantized GGUF source: https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF

Files

• Total layers: 47
• Valid split boundaries: 4, 8, 12, 16, 20, 24, 28, 32, 36, 40, 44
• Full-model equivalent: ~18.3 GB (same as Unsloth Q4_K_M)

Filenames use exclusive end indices (layers-{start}-{endExclusive}). The final chunk covers 3 layers (44–46).

Uses

Direct Use

Intended for Aquaduck / Arc (and compatible) runtimes that download and merge layer packages, not as a single drop-in file for stock llama.cpp.

For a normal single-file local run, use unsloth/GLM-4.7-Flash-GGUF or zai-org/GLM-4.7-Flash instead.

Use the base model’s GLM chat template; other formats will not work correctly. Recommended sampling (from Z.ai / Unsloth): temperature 1.0 , top-p 0.95 for general use; temperature 0.7 , top-p 1.0 for tool-calling. If using llama.cpp-compatible stacks, disable repeat penalty (or set it to 1.0 ) and prefer --min-p 0.01 .

Out-of-Scope Use

• Expecting any one chunk to run as a complete model
• Treating this repo as a new training run or re-quant
• Uses prohibited by the MIT license or Z.ai’s model card guidance

Bias, Risks, and Limitations

Same capabilities, biases, and risks as zai-org/GLM-4.7-Flash. Q4_K_M quantization (from Unsloth) can degrade quality vs. the original BF16 / higher-precision releases. Layer sharding does not change weights beyond packaging.

Recommendations

Follow Z.ai’s GLM-4.7 docs for chat template, reasoning, and tool use. Prefer the full Unsloth GGUF when you do not need staged loading.

How to Get Started

These shards are meant to be loaded automatically by an Aquaduck worker .

1. Install / open the Aquaduck desktop app and sign in as a worker.
2. Connect so the app can fetch your device’s model assignment from the model catalog ( zai-org/glm-4.7-flash ).
3. If model shards do not automatically download: Use Get latest assigned model (under Settings ). The worker will:
   • download only the contiguous layer-chunk GGUFs for your assigned stage from this repo
   • merge multi-chunk stages into one stage GGUF
   • keep that stage ready for split serving You do not need to pick individual *-layers-*.gguf files. Assignment and download are driven by model catalog metadata. This repo is not a single-file Q4_K_M drop-in for stock llama.cpp. For that, use https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF instead.

Training Details

No training. Weights come from Z.ai / GLM Team; Q4_K_M GGUF from Unsloth; this repo only splits that GGUF into layer packages.

Evaluation

No separate evals for the shards. See zai-org/GLM-4.7-Flash and https://arxiv.org/abs/2508.06471 .

Technical Specifications

• Architecture: GLM-4 MoE Lite (Glm4MoeLiteForCausalLM), ~30B params / ~3B active
• Quantization: Q4_K_M (Unsloth)
• Packaging: Arc gguf-shard / catalog catalog:split → *-layers-{start}-{endExclusive}.gguf
• Package format: layer-package-v1

Citation

@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},
}

Credit:

• Unsloth ( https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF ) for the GGUF quantization
• llama.cpp ( https://github.com/ggml-org/llama.cpp ) for GGUF support

Model Card Contact

Aquaduck AI — https://huggingface.co/aquaduck