| --- |
| license: apache-2.0 |
| base_model: OmniJev/OneJev-27B |
| library_name: transformers |
| datasets: |
| - OmniJev/OneJev-Data |
| pipeline_tag: image-text-to-text |
| tags: [onejev, system-one, decision-model, calibration, multimodal, gui-agent, video, fp8] |
| --- |
| |
|
|
| <p align="center"> |
| <picture> |
| <source media="(prefers-color-scheme: dark)" srcset="assets/banner-dark.svg"> |
| <img alt="OneJev-27B-FP8, a Multimodal System One Decision Model" src="assets/banner.svg" width="100%"> |
| </picture> |
| </p> |
| |
| <p align="center"> |
| <a href="https://huggingface.co/collections/OmniJev/onejev"><img alt="Hugging Face" src="https://img.shields.io/badge/Hugging_Face-OneJev-FFD21E?style=flat-square&logo=huggingface&logoColor=black"></a> |
| <a href="https://huggingface.co/spaces/BradNLP/OneJev"><img alt="Demo" src="https://img.shields.io/badge/Demo-Try_it-D45BB6?style=flat-square&logo=gradio&logoColor=white"></a> |
| <a href="https://github.com/OmniJev/OneJev"><img alt="GitHub" src="https://img.shields.io/badge/GitHub-OmniJev%2FOneJev-181717?style=flat-square&logo=github&logoColor=white"></a> |
| <a href="https://omnijev.github.io/OneJev/"><img alt="Website" src="https://img.shields.io/badge/Website-OneJev-0A84FF?style=flat-square&logo=googlechrome&logoColor=white"></a> |
| <a href="https://huggingface.co/datasets/OmniJev/OneJev-Data"><img alt="Data" src="https://img.shields.io/badge/Data-OneJev--Data-FF9D00?style=flat-square&logo=huggingface&logoColor=white"></a> |
| <a href="https://github.com/OmniJev/OneJev/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/badge/License-Apache_2.0-D22128?style=flat-square&logo=apache&logoColor=white"></a> |
| </p> |
|
|
| [OneJev-27B](https://huggingface.co/OmniJev/OneJev-27B) with its decoder weights in 8-bit floating point, one scale per weight row and per token: 30.4 GB instead of 54.7 GB, so it fits on one 48 GB GPU. On 229 test rows it gives the 16-bit model's answer on 226 (98.7%), accuracy 65.5 for 16-bit and 66.4 for 8-bit. It needs a GPU with FP8 (L40S, H100, H200 and newer). |
|
|
| On one H200 with a 1280x720 screenshot it answers 1 question in 168 ms and 10 questions in one request in 298 ms, against 189 ms and 324 ms for 16-bit. |
|
|
| ## Quick start |
|
|
| ```bash |
| pip install "qev[torch] @ git+https://github.com/OmniJev/OneJev.git" |
| qev serve --model OmniJev/OneJev-27B-FP8 |
| ``` |
|
|
| ```python |
| from qev import Client, Choice, Noul |
| from qev.media import data_uri |
| |
| r = Client("http://localhost:8000").system_one( |
| state={"task": "Pay the open invoice from ACME", "screen": "<image:1>"}, |
| media=[{"type": "image", "data": data_uri("screenshot.png")}], |
| questions={"done": Noul("The invoice has been paid"), |
| "next": Choice("What should the agent do next?", {"click": "click an element", "stop": "stop"})}, |
| ) |
| ``` |
|
|
| The server speaks TypeSafe's System One API plus a `media` field for images and video. More examples, the latency |
| benchmark and the code are on [GitHub](https://github.com/OmniJev/OneJev). |
|
|
| ## All sizes |
|
|
| | Model | Base | Weights | |
| |---|---|---:| |
| | [OneJev-0.8B](https://huggingface.co/OmniJev/OneJev-0.8B) | Qwen3.5-0.8B | 2.2 GB | |
| | [OneJev-4B](https://huggingface.co/OmniJev/OneJev-4B) | Qwen3.5-4B | 10.4 GB | |
| | [OneJev-9B](https://huggingface.co/OmniJev/OneJev-9B) | Qwen3.5-9B | 18.8 GB | |
| | [OneJev-27B](https://huggingface.co/OmniJev/OneJev-27B) | Qwen3.8-27B | 54.7 GB | |
| | **OneJev-27B-FP8** | OneJev-27B in 8-bit | 30.4 GB | |
|
|
| All sizes are in the [OneJev collection](https://huggingface.co/collections/OmniJev/onejev). |
|
|
| ## Citation |
|
|
| ```bibtex |
| @misc{onejev2026, |
| title = {{OneJev}: A Multimodal System One Decision Model}, |
| author = {{OmniJev Team}}, |
| year = {2026}, |
| howpublished = {\url{https://github.com/OmniJev/OneJev}} |
| } |
| ``` |
|
|
| ## License |
|
|
| Apache 2.0 |
|
|
