[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": ""},
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
