alt.freeweights.glm / GLM-4.7-Flash
From: zai-org <huggingface.co/zai-org>Newsgroups: alt.freeweights.glmSubject:

GLM-4.7-Flash

Date: 2026-11-14Commit: 7dd2089Signed: 2DC28CC7B26A283B ✓

Text generation model with 31.2B parameters. Safetensors weights, 62.5 GB in all. Published by zai-org under MIT.

31.2B params62.5GBGLM-4.7-Flashsafetensorspermissive
FactsParams31.2BSize62.5 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get zai-org/GLM-4.7-Flash
# manifest sha256 47a431dd5ad6… · 62.5 GB · 58 files
$ fw verify ./GLM-4.7-Flash zai-org/GLM-4.7-Flash
From sourceHosted (signed)zai-org/GLM-4.7-FlashLast check: 2026-11-14 06:31 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Overview

Size
62.5 GB
Weights
62.4 GB (safetensors)
Parameters
31.2B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
58, each with a sha256
Publisher
zai-org
Added
2026-11-14
Section
alt.freeweights.glm
Lineage

Original release from the publisher.

Where these bytes come from
Publisher at the pinned commitโ†’You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 06:31 UTCpassed

Model card

From the publisher at commit 7dd2089. Shown as plain text with links; images open at the publisher.

GLM-4.7-Flash#

Image: image

๐Ÿ‘‹ Join our Discord community.

๐Ÿ“– Check out the GLM-4.7 technical blog, technical report(GLM-4.5).

๐Ÿ“ Use GLM-4.7-Flash API services on Z.ai API Platform.

๐Ÿ‘‰ One click to GLM-4.7.

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#
BenchmarkGLM-4.7-FlashQwen3-30B-A3B-Thinking-2507GPT-OSS-20B
AIME 2591.685.091.7
GPQA75.273.471.5
LCB v664.066.061.0
HLE14.49.810.9
SWE-bench Verified59.222.034.0
ฯ„ยฒ-Bench79.549.047.7
BrowseComp42.82.2928.3
Evaluation Parameters#

Default Settings (Most Tasks)

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

For multi-turn agentic tasks (ฯ„ยฒ-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

ฯ„^2-Bench

  • Temperature: 0
  • Max new tokens: 16384

For ฯ„^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.

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#
  • using pip (must use pypi.org as the index url):
pip install -U vllm --pre --index-url https://pypi.org/simple --extra-index-url https://wheels.vllm.ai/nightly
pip install git+https://github.com/huggingface/transformers.git
SGLang#
  • Install the supported versions of SGLang and Transformers (using uv is recommended):
uv pip install sglang==0.3.2.dev9039+pr-17247.g90c446848 --extra-index-url https://sgl-project.github.io/whl/pr/
uv pip install git+https://github.com/huggingface/transformers.git@76732b4e7120808ff989edbd16401f61fa6a0afa
transformers#

using with transformers as

pip install git+https://github.com/huggingface/transformers.git

and then run:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_PATH = "zai-org/GLM-4.7-Flash"
messages = [{"role": "user", "content": "hello"}]
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
)
model = AutoModelForCausalLM.from_pretrained(
    pretrained_model_name_or_path=MODEL_PATH,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
inputs = inputs.to(model.device)
generated_ids = model.generate(**inputs, max_new_tokens=128, do_sample=False)
output_text = tokenizer.decode(generated_ids[0][inputs.input_ids.shape[1]:])
print(output_text)
vLLM#
vllm serve zai-org/GLM-4.7-Flash \
     --tensor-parallel-size 4 \
     --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
SGLang#
python3 -m sglang.launch_server \
  --model-path zai-org/GLM-4.7-Flash \
  --tp-size 4 \
  --tool-call-parser glm47  \
  --reasoning-parser glm45 \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --mem-fraction-static 0.8 \
  --served-model-name glm-4.7-flash \
  --host 0.0.0.0 \
  --port 8000
  • For Blackwell GPUs, include --attention-backend triton --speculative-draft-attention-backend triton in your SGLang launch command.

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}, 
}

Files

58 files ยท 62.5 GBWeights 62.4 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 58 files with their sha256
FileSizesha256
.eval_results/gpqa.yaml197 Bd6cbc1413ff508691275caf9972c58cea4db8c8083e943ec37ae6d1a4b844f61
.eval_results/hle.yaml186 B23e7499d8d3042fd203dcad1302d9529a3adbbc88be20c10d77dfff835e60419
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md8.17 KB7bfcbced42741ceb3fff8809f8d6c84ada9696850e257c4e53e6c2fe9ef4f9bf
chat_template.jinja3.12 KBd63ad536c3c81880043e22ec7fd08db42b4d8fb7c89c7138bc562bfa25281375
config.json1.07 KBdc9b97c7c9bed726a2e6939da4234d5c43abb3edec8812068c9a1af1dbc13acb
generation_config.json181 Be19f4eb8be12cdb62a3737b52a332c7c142cbf5ee24a5de7d806f6132b782425
model-00001-of-00048.safetensors1.44 GB90abe0d075755853145c96906a1300f57c167fcc9aa67221239b448abf54933c
model-00002-of-00048.safetensors1.27 GB8c51e2434efe609cbe652014a924e088a5ea97be35ca29cfa893a1a9a90304b1
model-00003-of-00048.safetensors1.27 GBab6ebdd01af10c9bde1ec0b2a182d6f7ff8df831add6810695e5f3b50918040d
model-00004-of-00048.safetensors1.27 GB932e4dbb8f7583d2b6392a6e850dd7aa05636827e8b90ff7858cae709838dca7
model-00005-of-00048.safetensors1.27 GB7f56a3e52bf5905c2df07ef53575ae8e62622138a15b0affc2b3f84785ca81e9
model-00006-of-00048.safetensors1.27 GB83aa0eeca6e5a9394bb8a1c9cab46cc603799d729cf64ed4bbc341e0a7085feb
model-00007-of-00048.safetensors1.27 GBa9679076d3bd10c5f1287d12418fddb41c8b54b8c8ccc0672796ef7e8431b797
model-00008-of-00048.safetensors1.27 GB7d1231577a057ff957d480c277e497910acbba75fc9232f8fd8f44c1a647d7a2
model-00009-of-00048.safetensors1.27 GB095d626626773284535ba4114c2b320003ba3c8430bd104f5e7bba3772b2a1b1
model-00010-of-00048.safetensors1.27 GBc3f8d197b0d253082f547d67989b1e3928a742b508f6f8d4abf119f3ba2990ed
model-00011-of-00048.safetensors1.27 GBa8b7eeef625a6ed9ced479e064870f0ebf0da67056cd5e582300d0ebcf44de21
model-00012-of-00048.safetensors1.27 GB49adb8b9f02d1643ab22406b0e05938ce3d7a8986fd0981e0af5d4cd47ee8b12
model-00013-of-00048.safetensors1.27 GBf269382ae6ce42cd05937fcd5551e08da151c810a87bb0e1994ff9bb5f9eb7c9
model-00014-of-00048.safetensors1.27 GBacd6f36aadceda658a5db6fc6a04160ae2ca1ae78d4a9c84aeabcea8e80b44c8
model-00015-of-00048.safetensors1.27 GB606079fe1e000d658142c59fee66aa8d7c949d758612debd78d21cde2fae392c
model-00016-of-00048.safetensors1.27 GBb53fb45f7689b505fc185180503ea9d45af67042ba38914e53bbdee97173c974
model-00017-of-00048.safetensors1.27 GBa51e478badd50bb9b5299e3ad7979bfd40da8ab96983de0cd16a0fb5fddb4bc9
model-00018-of-00048.safetensors1.27 GB680295c83f29a90c97f2d68c1290a152330c2dbd3654abdf0f074e6d8018062c
model-00019-of-00048.safetensors1.27 GB355f9437e291b0846b5ecac1d644766ec17bd4863da441e4e786f33d7bac3347
model-00020-of-00048.safetensors1.27 GB8f8d4698fc5ce834021254b407c61e5376a693dcafeb996a8fc708639b44aed8
model-00021-of-00048.safetensors1.27 GB111570fc7f55bcb9beb7bcb969475b27ffbcad97b95788464ff91a1e07ff897a
model-00022-of-00048.safetensors1.27 GBced6a73df393df3bd559fc69093763fb5cc9fedee31e245a52a7786939199896
model-00023-of-00048.safetensors1.27 GBb287bb0ce12a1ac975978c94548f2bbab3267e83e0c888871a3ada3ddf91405d
model-00024-of-00048.safetensors1.27 GBc6e77476f0f57dc0386b64741d9251632d46e646faab6780d10a5a6a5f456668
model-00025-of-00048.safetensors1.27 GB8f9e643d9d3e9152b9156424615c8054cffe6b8bc1b776567da17bbd3b97ebcb
model-00026-of-00048.safetensors1.27 GB634da561277b9b77410a319bd930e940d443055fb688a2e4b9574aae1569192d
model-00027-of-00048.safetensors1.27 GB3286537b5a5dd2b4742878476601a4f5b1f061e948386babe05076fd058fa5ec
model-00028-of-00048.safetensors1.27 GB56335c906d44c1c6f37530d65182cd6af4fb146fa8a68e8e510d6419b5b007e7
model-00029-of-00048.safetensors1.27 GB3e6591dfb36a59918f91c152ba0baf184b4372c667fe46f74024e5d8ae86f378
model-00030-of-00048.safetensors1.27 GB62373b800980841e6ca5c4c48db570729246092d03ac756bdeb55ecfdd599a2c
model-00031-of-00048.safetensors1.27 GB332d82cefb0b4d87c48e3e989c97d3e74b6f64326313694ed226a72bf26e3b99
model-00032-of-00048.safetensors1.27 GB0f9897915eef55f41b221ff072d8b0b401e447007d648b63ddabf9b795361c18
model-00033-of-00048.safetensors1.27 GB29059fb79e6fefaad49b7c2833370cd78079b403cc98bc28ce95976207840f7f
model-00034-of-00048.safetensors1.27 GBf989cc8af19949a310599c5ab8d65f0ae8406908e1a702588b892604179061a1
model-00035-of-00048.safetensors1.27 GBaaa91e9b1a075d1753e45a01db198ed48f2739392e46e1843a4dcaaab6cd02eb
model-00036-of-00048.safetensors1.27 GBcf807da31533424a54196cd07da6caa1a22199b72d822bd8c2f387172b6e1c65
model-00037-of-00048.safetensors1.27 GB887aeb5568ef6189a7618309e50f0277ad339da86133526ca6d820b88ecbb5d4
model-00038-of-00048.safetensors1.27 GB036a38cc10858a8cc5a2fcd09fdab1b53258d04ff87dc4d3d21f140c54b029dd
model-00039-of-00048.safetensors1.27 GB62ae341291fe720719ab6cdcf2348752f262f4575a3f8221b353deb224bcbd1d
model-00040-of-00048.safetensors1.27 GBcd8af33462a3f7b4dbc5393da4016acffabafc20b826f952e912adb2a2845fe3
model-00041-of-00048.safetensors1.27 GB39098c9b6770ff5c185a70b8f0d6cfca22f95e3c47dc38de88c3d2ec2b1cf5bc
model-00042-of-00048.safetensors1.27 GBffe0b23aab19b608ca59f46628064c3d53d846c81d6f978c2579b38e09e35747
model-00043-of-00048.safetensors1.27 GBefe1da68f8c30d7e77a68d48eb7d65d28709f536062dba8168490370cca47ba4
model-00044-of-00048.safetensors1.27 GBa731baa1370864ad61cf8fe8000cb8e1e266529206824a3ce96b5229eb3c53c8
model-00045-of-00048.safetensors1.27 GBa636f872a931396d2fdc57b6c715294e14b3c8040420ffce856a2a0a18194916
model-00046-of-00048.safetensors1.27 GBba5365e31c27cd13e330a7135f7251f3bf16e99c8504acffa9e8190b585eb773
model-00047-of-00048.safetensors2.54 GB1bcc5d06065d2a564894657945ccfe9411762421c2c60acf91de31050cd4d84d
model-00048-of-00048.safetensors1.29 GB35fff90a30ca808d86dc24f9e3eda119832ab69fb1f88ae4cccfbf0e5ee409a1
model.safetensors.index.json872 KB91e6e95ca21700f50904a680c8c4212f5aa16dc7c10a013f01c906957c889791
tokenizer.json20.2 MB19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
tokenizer_config.json7.23 KB31a173e2797ddc8b72ac996803513e627fc28d7aad02cfcce321a431d865c86d
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
7dd20894a6 pinned now2026-11-14 06:31 UTC58 files ยท 62.5 GB

Use it

$ fw get zai-org/GLM-4.7-Flash
# manifest sha256 47a431dd5ad6… · 62.5 GB · 58 files
$ fw verify ./GLM-4.7-Flash zai-org/GLM-4.7-Flash
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/zai-org/GLM-4.7-Flash.json --dir ./GLM-4.7-Flash $ python3 fw.py verify ./GLM-4.7-Flash ./zai-org__GLM-4.7-Flash.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download zai-org/GLM-4.7-Flash --revision 7dd20894a642a0aa287e9827cb1a1f7f91386b67 --local-dir ./GLM-4.7-Flash
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("zai-org/GLM-4.7-Flash", revision="7dd20894a642a0aa287e9827cb1a1f7f91386b67") model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4.7-Flash", revision="7dd20894a642a0aa287e9827cb1a1f7f91386b67", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve zai-org/GLM-4.7-Flash --revision 7dd20894a642a0aa287e9827cb1a1f7f91386b67

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Checked and recorded in the license audit. 2026-11-14
Text in
README.md
Text sha256
7bfcbced42741ceb3fff8809f8d6c84ada9696850e257c4e53e6c2fe9ef4f9bf
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: zai-org <huggingface.co/zai-org>Newsgroups: alt.freeweights.glmSubject: GLM-4.7-FlashDate: 2026-11-14Commit: 7dd2089Signed: 2DC28CC7B26A283B ✓
Upstream
zai-org/GLM-4.7-Flash
Pinned commit
7dd20894a642a0aa287e9827cb1a1f7f91386b67
Manifest
GLM-4.7-Flash.json ยท .minisig
Manifest sha256
47a431dd5ad68bd2cd97106d33b52915d53645073c46b9d1f1e4865f968a1c66
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:31 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/zai-org/GLM-4.7-Flash.json $ curl -O https://freeweights.allternit.com/manifests/zai-org/GLM-4.7-Flash.json.minisig $ minisign -Vm GLM-4.7-Flash.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

13 models in the catalog name this one as their parent.

Quantizations
13
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download zai-org/GLM-4.7-Flash
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. GLM-4.7-Flash.json. Provenance. Takedown history: none.

Variants

13 quantized or adapter builds of GLM-4.7-Flash. Each has its own license check and page.

From: bartowski <huggingface.co/bartowski>Subject: arcee-ai_GLM-4-32B-Base-32K-GGUF
From: ggml-org <huggingface.co/ggml-org>Subject: AutoGLM-Phone-9B-GGUF
From: zai-org <huggingface.co/zai-org>Subject: cogagent-chat-hf
From: zai-org <huggingface.co/zai-org>Subject: CogView3-Plus-3B
From: zai-org <huggingface.co/zai-org>Subject: cogvlm-base-490-hf
From: laion <huggingface.co/laion>Subject: dev_set_part1_10k_glm_4_7_traces_jupiter