alt.freeweights.text / GELab-Zero-4B-preview
From: stepfun-ai <huggingface.co/stepfun-ai>Newsgroups: alt.freeweights.textSubject:

GELab-Zero-4B-preview

Date: 2026-11-15Commit: 838a527Signed: 2DC28CC7B26A283B ✓

Image text to text model with 4.4B parameters. Safetensors weights, 8.89 GB in all. Published by stepfun-ai under Apache-2.0.

4.4B params8.89GBGELab-Zero-4B-previewsafetensorspermissive
FactsParams4.4BSize8.89 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get stepfun-ai/GELab-Zero-4B-preview
# manifest sha256 44559cc47151… · 8.89 GB · 19 files
$ fw verify ./GELab-Zero-4B-preview stepfun-ai/GELab-Zero-4B-preview
From sourceHosted (signed)stepfun-ai/GELab-Zero-4B-previewLast check: 2026-11-15 03:32 UTC

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

Fine-tune of Qwen3-VL-4B-Instruct.

Works with

Overview

Size
8.89 GB
Weights
8.88 GB (safetensors)
Parameters
4.4B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
19, each with a sha256
Publisher
stepfun-ai
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-VL-4B-Instruct

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 03:32 UTCpassed

Model card

From the publisher at commit 838a527. Shown as plain text with links; images open at the publisher.

GELab-Zero-4B-preview#

This model is part of the GELab-Zero project, which presents the Step-GUI Technical Report [Paper] [Project Page] [Code].

Model Details#

This model is part of the GELab-Zero project, which aims to accelerate the innovation and application deployment of GUI Agents by providing:

  1. A 4B GUI Agent model capable of running on local computers.
  2. Plug-and-play inference infrastructure that handles ADB connections, dependency installation, and task recording/replay (available in the GELab-Zero).
Key Capabilities#
  • Local Deployment: Optimized for consumer-grade hardware, balancing low latency with privacy.
  • GUI Navigation: Proficient in detecting and interacting with UI elements (click, type, slide, wait, etc.) based on visual cues.
  • Complex Task Execution: Handles multi-step long-horizon tasks across various apps (Food, Transportation, Shopping, Social, etc.).
  • Open-World Generalization: Capable of zero-shot operation across diverse unseen applications and complex dynamic interfaces without requiring app-specific adaptation.

Usage#

Quick Start with Ollama#

The easiest way to run inference is using Ollama.

1.Install Ollama: Download from ollama.com.

2.Download the Model:

# Install huggingface-cli
pip install huggingface_hub
# Download model
huggingface-cli download --resume-download stepfun-ai/GELab-Zero-4B-preview --local-dir gelab-zero-4b-preview

3.Create and Run in Ollama:

cd gelab-zero-4b-preview
ollama create gelab-zero-4b-preview -f Modelfile
    
# Test the model
curl -X POST http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
        "model": "gelab-zero-4b-preview",
        "messages": [{"role": "user", "content": "Hello, GELab-Zero!"}]
      }'

To use this model for actual Android device control (ADB connection, task execution), please use the GELab-Zero.

Citation#

If you find GELab-Zero-4B-preview useful for your research, please consider citing our work :)

@misc{yan2025stepguitechnicalreport,
      title={Step-GUI Technical Report}, 
      author={Haolong Yan and Jia Wang and Xin Huang and Yeqing Shen and Ziyang Meng and Zhimin Fan and Kaijun Tan and Jin Gao and Lieyu Shi and Mi Yang and Shiliang Yang and Zhirui Wang and Brian Li and Kang An and Chenyang Li and Lei Lei and Mengmeng Duan and Danxun Liang and Guodong Liu and Hang Cheng and Hao Wu and Jie Dong and Junhao Huang and Mei Chen and Renjie Yu and Shunshan Li and Xu Zhou and Yiting Dai and Yineng Deng and Yingdan Liang and Zelin Chen and Wen Sun and Chengxu Yan and Chunqin Xu and Dong Li and Fengqiong Xiao and Guanghao Fan and Guopeng Li and Guozhen Peng and Hongbing Li and Hang Li and Hongming Chen and Jingjing Xie and Jianyong Li and Jingyang Zhang and Jiaju Ren and Jiayu Yuan and Jianpeng Yin and Kai Cao and Liang Zhao and Liguo Tan and Liying Shi and Mengqiang Ren and Min Xu and Manjiao Liu and Mao Luo and Mingxin Wan and Na Wang and Nan Wu and Ning Wang and Peiyao Ma and Qingzhou Zhang and Qiao Wang and Qinlin Zeng and Qiong Gao and Qiongyao Li and Shangwu Zhong and Shuli Gao and Shaofan Liu and Shisi Gao and Shuang Luo and Xingbin Liu and Xiaojia Liu and Xiaojie Hou and Xin Liu and Xuanti Feng and Xuedan Cai and Xuan Wen and Xianwei Zhu and Xin Liang and Xin Liu and Xin Zhou and Yingxiu Zhao and Yukang Shi and Yunfang Xu and Yuqing Zeng and Yixun Zhang and Zejia Weng and Zhonghao Yan and Zhiguo Huang and Zhuoyu Wang and Zheng Ge and Jing Li and Yibo Zhu and Binxing Jiao and Xiangyu Zhang and Daxin Jiang},
      year={2025},
      eprint={2512.15431},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.15431}, 
}

@software{gelab_zero_2025,
  title={GELab-Zero: An Advanced Mobile Agent Inference System},
  author={GELab Team},
  year={2025},
  url={https://github.com/stepfun-ai/gelab-zero}
}

@misc{gelab_engine,
      title={GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning}, 
      author={Haolong Yan and Yeqing Shen and Xin Huang and Jia Wang and Kaijun Tan and Zhixuan Liang and Hongxin Li and Zheng Ge and Osamu Yoshie and Si Li and Xiangyu Zhang and Daxin Jiang},
      year={2025},
      eprint={2512.02423},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.02423}, 
}

Files

19 files · 8.89 GBWeights 8.88 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 19 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
Modelfile147 Bd6dba5e52151f62253512e7eaa3be125395c162545f385e3fe21811aec345b57
README.md4.97 KB9c9ba531514a471b1bce4e3ba70b4a056594f108de0b82de2bfa5c9e55b230d5
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja5.29 KB3636d0f0bd6bef02654cdffdc447b79cb2cef8ab02cc75267345946291a489e4
chat_template.json5.50 KB6f8a6a55027e3da5160105556cda5dd69f6423f1c32645f6730d32de7773d0c4
config.json1.68 KBaeda63a91d24a69c08431363b525799defd15e0280c5fd180fda708c73fc40f2
configuration.json73 Bf888421726665e8a84b738eed42a64875aed79de8be7daade851ac8bf4c0cef9
generation_config.json269 B7da06aec250a14bd9319a663779d6081d0d3a484681745d2541070e720749e27
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00002.safetensors4.99 GB5b8c5bdc506cf6ea774cd9bc6459bb81232d4417a415abecd25204ecfa600f56
model-00002-of-00002.safetensors3.89 GBb1abacb612bfce3b1008003c1f8571c9dff6ed29a3cbb8dba91c434c01aec35d
model.safetensors.index.json64.7 KB1f83d0186afc6571059fe2cd3860fb9b7d31bee748c9703cbe9e9f419a394587
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.45 KB81ec7bb9530159b326c0bef1d0b6c33d392090524014ea3f0123a3c1eb9c2af5
video_preprocessor_config.json817 B59c5c9eb52182eb14c06ffb10ca9effd29adce5f238a95de23ca14a38dbd2cb1
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
838a527e40 pinned now2026-11-15 03:32 UTC19 files · 8.89 GB

Use it

$ fw get stepfun-ai/GELab-Zero-4B-preview
# manifest sha256 44559cc47151… · 8.89 GB · 19 files
$ fw verify ./GELab-Zero-4B-preview stepfun-ai/GELab-Zero-4B-preview
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/stepfun-ai/GELab-Zero-4B-preview.json --dir ./GELab-Zero-4B-preview $ python3 fw.py verify ./GELab-Zero-4B-preview ./stepfun-ai__GELab-Zero-4B-preview.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download stepfun-ai/GELab-Zero-4B-preview --revision 838a527e40fe9c49f76f4e7d483d75de48de23e7 --local-dir ./GELab-Zero-4B-preview
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("stepfun-ai/GELab-Zero-4B-preview", revision="838a527e40fe9c49f76f4e7d483d75de48de23e7") model = AutoModelForImageTextToText.from_pretrained("stepfun-ai/GELab-Zero-4B-preview", revision="838a527e40fe9c49f76f4e7d483d75de48de23e7", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve stepfun-ai/GELab-Zero-4B-preview --revision 838a527e40fe9c49f76f4e7d483d75de48de23e7

License

Name
Apache License 2.0
Id
Apache-2.0
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
9c9ba531514a471b1bce4e3ba70b4a056594f108de0b82de2bfa5c9e55b230d5
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: stepfun-ai <huggingface.co/stepfun-ai>Newsgroups: alt.freeweights.textSubject: GELab-Zero-4B-previewDate: 2026-11-15Commit: 838a527Signed: 2DC28CC7B26A283B ✓
Upstream
stepfun-ai/GELab-Zero-4B-preview
Pinned commit
838a527e40fe9c49f76f4e7d483d75de48de23e7
Manifest
GELab-Zero-4B-preview.json · .minisig
Manifest sha256
44559cc471519a378282f7fbbad4f97a24bf9cc45c6fb21dcbbd5343f1545c9a
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:32 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/stepfun-ai/GELab-Zero-4B-preview.json $ curl -O https://freeweights.allternit.com/manifests/stepfun-ai/GELab-Zero-4B-preview.json.minisig $ minisign -Vm GELab-Zero-4B-preview.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

Qwen/Qwen3-VL-4B-Instruct · this model is a finetune of it

1 model in the catalog name this one as their parent.

Quantizations
1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download stepfun-ai/GELab-Zero-4B-preview
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. GELab-Zero-4B-preview.json. Provenance. Takedown history: none.

Variants

1 quantized or adapter build of GELab-Zero-4B-preview. Each has its own license check and page.

From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B