---
title: OneJev-27B-FP8
canonical_url: "https://www.modelscope.ai/models/OmniJev/OneJev-27B-FP8"
md_url: "https://www.modelscope.ai/models/OmniJev/OneJev-27B-FP8.md"
repository: OmniJev/OneJev-27B-FP8
last_updated: 2026-10-19
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
base_model:
  - OmniJev/OneJev-27B
base_model_relation: quantized
parameters: 27.4B
tensor_type:
  - BF16
  - F8_E4M3
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 37
stars: 0
tags:
  - onejev
  - system-one
  - decision-model
  - calibration
  - multimodal
  - gui-agent
  - video
  - fp8
---

# OneJev-27B-FP8

> OneJev-27B-FP8 - An open-source model by OmniJev on ModelScope. 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…

OmniJev/OneJev-27B-FP8 is a 27.4B-parameter image-text-to-text model on ModelScope. licensed under apache-2.0. derived from OmniJev/OneJev-27B.

- **Repository**: OmniJev/OneJev-27B-FP8
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 27.4B
- **Base model**: OmniJev/OneJev-27B
- **Tags**: onejev, system-one, decision-model, calibration, multimodal, gui-agent, video, fp8
- **Downloads**: 37
- **Stars**: 0
- **Last updated**: 2026-10-19

Source: https://www.modelscope.ai/models/OmniJev/OneJev-27B-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-F83800?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