alt.freeweights.glm / GLM-4.7-Flash-NVFP4
From: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.glmSubject:

GLM-4.7-Flash-NVFP4

Date: 2026-11-15Commit: 98b0362Signed: 2DC28CC7B26A283B ✓

Text generation model with 16.7B parameters. Safetensors weights, 21.3 GB in all. Published by unsloth under MIT.

16.7B params21.3GBGLM-4.7-Flash-NVFP4safetensorspermissive
FactsParams16.7BSize21.3 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get unsloth/GLM-4.7-Flash-NVFP4
# manifest sha256 749b71ce9374… · 21.3 GB · 12 files
$ fw verify ./GLM-4.7-Flash-NVFP4 unsloth/GLM-4.7-Flash-NVFP4
From sourceHosted (signed)unsloth/GLM-4.7-Flash-NVFP4Last check: 2026-11-15 05:07 UTC

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

Quantized of GLM-4.7-Flash.

Works with

Overview

Size
21.3 GB
Weights
21.3 GB (safetensors)
Parameters
16.7B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
12, each with a sha256
Publisher
unsloth
Added
2026-11-15
Section
alt.freeweights.glm
Lineage

Original release from the publisher.

Base model: zai-org/GLM-4.7-Flash

Where these bytes come from
Publisher at the pinned commit→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.co2026-11-15 05:07 UTCpassed

Model card

From the publisher at commit 98b0362. Shown as plain text with links; images open at the publisher.

Note. Includes Unsloth chat template fixes!

For llama.cpp, use --jinja

Read our How to Run NVFP4 quants Guide!#

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

https://github.com/unslothai/unsloth/ https://discord.gg/unsloth https://docs.unsloth.ai/

Run in vLLM#

uv venv unsloth-nvfp4-env --python 3.13
source unsloth-nvfp4-env/bin/activate
uv pip install "vllm>=0.25.0" "flashinfer-python>=0.6.13" "nvidia-cutlass-dsl>=4.5.2" --torch-backend=auto
VLLM_ATTENTION_BACKEND=TRITON_MLA vllm serve unsloth/GLM-4.7-Flash-NVFP4

Do not use the Marlin backend (around 2x slower); let vLLM auto-select the NVFP4 kernel.

GLM-4.7-Flash#

Image: image

👋 Join our Discord community.

📖 Check out the GLM-4.7 technical blog, technical report(GLM-4.5).

📍 Use GLM-4.7-Flash API services on Z.ai API Platform.

👉 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
τ²-Bench79.549.047.7
BrowseComp42.82.2928.3

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#
  • using pip install sglang from source, then update transformers to the latest main branch.
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

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

12 files · 21.3 GBWeights 21.3 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md8.43 KBd42ef346ae623422ecc043143b34931ffeadc536001b6aa92625c80d71838703
chat_template.jinja3.12 KBd63ad536c3c81880043e22ec7fd08db42b4d8fb7c89c7138bc562bfa25281375
config.json6.38 KBc9a94c0b43288570173f7ad359a5ca2428f1c1d95857817f4af74deaa409efc4
generation_config.json215 B80b2a0d01dfb732996aedb98868fee474e9fc5f46553df3a3f5a97ad0fb2b68a
model.safetensors18.7 GB321196f10d90e4bbf3c2401bb49a6a4062cbd99701673160fcdf78b56b8865f1
model.safetensors.index.json3.00 MB839906024a440f91db46ddc8898dde3cc5b5e148441bccfafd762d927624ce84
model_mtp.safetensors2.56 GB6c5e76856a6f306161e17baefb92e226465aba0841d9638513dc056b8cfb39ff
recipe.yaml719 Bbbbf047be7500829b58dfde401c6d8ca926f45ea25a3dc8d115483491f99daef
special_tokens_map.json710 B946f6f7ed989038aa262abffbc134995e9a5e5d2aba596ba57769414ac8a25e4
tokenizer.json20.2 MBfcce46e83a6ed162239b0a0b421d2ab3f148d3f1fd6839c0f82baf61b2284cdc
tokenizer_config.json785 B278c313bea224323f05aa03b8855c3f2b8bb744de6f5f9cc758970159b3715c8
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
98b0362133 pinned now2026-11-15 05:07 UTC12 files · 21.3 GB

Use it

$ fw get unsloth/GLM-4.7-Flash-NVFP4
# manifest sha256 749b71ce9374… · 21.3 GB · 12 files
$ fw verify ./GLM-4.7-Flash-NVFP4 unsloth/GLM-4.7-Flash-NVFP4
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/GLM-4.7-Flash-NVFP4.json --dir ./GLM-4.7-Flash-NVFP4 $ python3 fw.py verify ./GLM-4.7-Flash-NVFP4 ./unsloth__GLM-4.7-Flash-NVFP4.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/GLM-4.7-Flash-NVFP4 --revision 98b0362133bda9ee3b1b875636636c07861f5947 --local-dir ./GLM-4.7-Flash-NVFP4
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("unsloth/GLM-4.7-Flash-NVFP4", revision="98b0362133bda9ee3b1b875636636c07861f5947") model = AutoModelForCausalLM.from_pretrained("unsloth/GLM-4.7-Flash-NVFP4", revision="98b0362133bda9ee3b1b875636636c07861f5947", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve unsloth/GLM-4.7-Flash-NVFP4 --revision 98b0362133bda9ee3b1b875636636c07861f5947

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
d42ef346ae623422ecc043143b34931ffeadc536001b6aa92625c80d71838703
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: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.glmSubject: GLM-4.7-Flash-NVFP4Date: 2026-11-15Commit: 98b0362Signed: 2DC28CC7B26A283B ✓
Upstream
unsloth/GLM-4.7-Flash-NVFP4
Pinned commit
98b0362133bda9ee3b1b875636636c07861f5947
Manifest
GLM-4.7-Flash-NVFP4.json · .minisig
Manifest sha256
749b71ce937450396838f03941b1b4ded6e4fff7cc1f1212bf2aa7203237dec7
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:07 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/unsloth/GLM-4.7-Flash-NVFP4.json $ curl -O https://freeweights.allternit.com/manifests/unsloth/GLM-4.7-Flash-NVFP4.json.minisig $ minisign -Vm GLM-4.7-Flash-NVFP4.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

Parent

zai-org/GLM-4.7-Flash · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/GLM-4.7-Flash-NVFP4
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-NVFP4.json. Provenance. Takedown history: none.
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