Instructions to use OmniJev/OneJev1.6-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OmniJev/OneJev1.6-4B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="OmniJev/OneJev1.6-4B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("OmniJev/OneJev1.6-4B")
model = AutoModelForMultimodalLM.from_pretrained("OmniJev/OneJev1.6-4B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OmniJev/OneJev1.6-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OmniJev/OneJev1.6-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OmniJev/OneJev1.6-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/OmniJev/OneJev1.6-4B

SGLang

How to use OmniJev/OneJev1.6-4B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OmniJev/OneJev1.6-4B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OmniJev/OneJev1.6-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OmniJev/OneJev1.6-4B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OmniJev/OneJev1.6-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use OmniJev/OneJev1.6-4B with Docker Model Runner:
```
docker model run hf.co/OmniJev/OneJev1.6-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OneJev1.6-4B is the 4B model of OneJev 1.6, a multimodal System One decision model. Give it a screenshot, a photo, a video or plain text along with a few typed questions, and it returns a calibrated probability for every option in a single forward pass. It is a full fine-tune of Qwen/Qwen3.5-4B on about 440,000 questions drawn from real agent runs, videos, images and the training splits of public decision datasets.

Decision Index

On the public part of Decision Index 0.3 (37 benchmarks, 140,178 requests, run and scored with the board's own kit), OneJev1.6-4B scores 62.01, up from 54.89 for OneJev1.5-4B. Every model on the board that scores higher has 25B parameters or more. It has the best score in four of the five areas among the five models below, and the second best in Language Understanding.

Decision Index public part, table: OneJev1.6-4B 62.01 against Perplexity Decider Flash v1.2 (4B) 60.06, CoCo-Decision-4B 2.3.0 55.38, vLLM-SR d3-mini (4B) 54.90, RSI-Jev v6.1 VL 4B 50.98, overall and in each of the five areas; best value in each row in magenta, second best in light pink

The four other models are the highest-scoring models of 3B to 6B parameters on the board.

It also scores above 42 of the 57 models of 25B to 36B parameters on the board.

Decision Index public part: OneJev1.6-4B 62.0 at 4.5B parameters against Cloudflare clef 61.7, Nace.AI Drex v2.0 61.2, Quyet-1.0 Large 60.8, MORJ 1.0.1 60.2, Sieve 27B 60.0, AnyJev L0 59.8 at 28B to 35B

Other models' scores are their public-part scores on the board on 16 October 2026.

Results

Results table: OneJev1.6-4B against Jev 1.13, Jev-Omni 12B and Qwen3.8-27B thinking; best score in each row in magenta, second best in light pink

Accuracy in percent. The OneJev test set holds questions of the training kinds that no model saw in training. Jev 1.13's scores are its published ones, and it reads text only.

Quick start

pip install "qev[torch] @ git+https://github.com/OmniJev/OneJev.git"
qev serve --model OmniJev/OneJev1.6-4B

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 and the code are on GitHub.

Citation

@misc{onejev2026,
  title        = {{OneJev}: A Multimodal System One Decision Model},
  author       = {{OmniJev Team}},
  year         = {2026},
  howpublished = {\url{https://github.com/OmniJev/OneJev}}
}