d3-edge

d3-edge is the 0.6B multimodal foundation decision model of Decision 3.0, the decision models of vLLM Semantic Router. Give it an input (text or JSON, optionally with images and videos) and the questions you need answered: pick one of several options, say yes or no, or rate on a scale. It answers them all in one call and returns a probability for every answer, without generating text.


Parameters	0.66B, including the 0.10B vision encoder
Inputs	Text or JSON, plus images and videos (several per request)
Decision types	Choice · Yes / No · Score
License	Apache-2.0

Highlights

Jev Decision Index 0.3, public suite: 30.55, measured with the official 0.3 kit on the released weights: all 140,178 public requests answered, none unsupported.
+13.9 on the public suite over Decision 2.0 (its 0.6B model: 16.68 on the board), ahead in all five areas.
Reads images: multiple images per request (PNG, JPEG or WebP), given as paths, URLs, PIL images or base64 data URLs; every question of the request sees all of them.
Reads videos: multiple videos per request (MP4, WebM, MOV or MKV), given as paths, URLs, base64 data URLs or frame arrays, read at 2 frames per second; Perception Test (multiple-choice video QA): 47.5 (internal evaluation).
Speed: a median of 8.6 ms for a text request, 42.5 ms for a request with an image and 311.8 ms for a request with a 10-second video, on one AMD Instinct MI325X GPU, one request at a time.
Many questions, one call: Choice, Yes / No and Score questions about the same input are answered together, each from its own forward pass over the input, with a probability for every option.

Quickstart

pip install "transformers==5.17.0" torch torchvision pillow opencv-python-headless safetensors accelerate
pip install flash-linear-attention  # optional: fast GPU kernels for the linear-attention layers

import json

from huggingface_hub import hf_hub_download
from transformers import AutoModel

model = AutoModel.from_pretrained("vllm-sr/d3-edge", trust_remote_code=True)

# Text
result = model.system_one(
    state="The order arrived damaged yesterday. The customer has a receipt and asks for a replacement today.",
    questions={
        "route": {
            "type": "choice",
            "instructions": "Which team should handle this request?",
            "criteria": {
                "returns": "Refunds, replacements and damaged deliveries",
                "billing": "Payments, invoices and charges",
                "technical": "Product setup and faults"
            }
        },
        "receipt": {
            "type": "noul",
            "instructions": "Does the customer have a receipt?"
        },
        "urgency": {
            "type": "score",
            "instructions": "How urgent is this request?",
            "criteria": [
                "Routine",
                "Soon",
                "Today"
            ]
        }
    },
)
print(json.dumps(result["answers"], indent=2))

# Text and an image (or several)
receipt = hf_hub_download("vllm-sr/d3-edge", "assets/example-receipt.png")
result = model.system_one(
    state="The customer says the blender arrived cracked and attached the receipt.",
    images=[receipt],  # local paths, http(s) URLs, PIL images or base64 data URLs
    questions={
        "route": {
            "type": "choice",
            "instructions": "Which team should handle this request?",
            "criteria": {
                "returns": "Refunds, replacements and damaged deliveries",
                "billing": "Payments, invoices and charges",
                "technical": "Product setup and faults"
            }
        },
        "on_receipt": {
            "type": "noul",
            "instructions": "Does the receipt list the blender?"
        },
        "payment": {
            "type": "choice",
            "instructions": "How was the order paid?",
            "criteria": {
                "card": None,
                "cash": None,
                "gift card": None
            }
        }
    },
)
print(json.dumps(result["answers"], indent=2))

# Text and a video (or several)
clip = hf_hub_download("vllm-sr/d3-edge", "assets/example-video.mp4")
result = model.system_one(
    state="A short clip from a test camera.",
    videos=[clip],  # local paths, http(s) URLs, base64 data URLs or frame arrays
    questions={
        "direction": {
            "type": "choice",
            "instructions": "Which way does the square move?",
            "criteria": {
                "right": "From left to right",
                "left": "From right to left",
                "still": "It does not move"
            }
        },
        "color_change": {
            "type": "noul",
            "instructions": "Does the square change color?"
        }
    },
)
print(json.dumps(result["answers"], indent=2))

# Or as a pipeline:
# transformers.pipeline("decision", model="vllm-sr/d3-edge", trust_remote_code=True)(state=..., questions=..., images=..., videos=...)

Images go before the text of the request, each read at up to 1.6 megapixels; videos follow the images, read at 2 frames per second (at most 32 frames spread over the whole video, each at up to 0.2 megapixels). Every question of the request sees all of them.

Evaluation

Text: Jev Decision Index 0.3.1

Model	Jev Decision Index ↑	Public ↑	Same-skill tests ↑	New-domain tasks ↑
d3-edge	19.7	30.6	25.4	9.4
Bekko System One v0 400M	15.2	22.5	21.6	7.2
Dinah-0	13.9	26.1	18.8	5.5
Decision 2.0 (0.6B)	13.6	16.7	16.9	11.8
LiquidAI d1-omni-600M	9.5	17.9	13.6	5.1
GLiNER2.5-Decide	9.2	11.5	12.1	9.6

Images: Jev Decision Index vision board 0.3.1

Model	Vision Index ↑	Public ↑	Private ↑
d3-edge	38.8	41.0	36.6

d3-edge on the public vision benchmarks († approximate rebuild):

Benchmark	d3-edge
CV-Bench	58.6
BLINK	34.1
RealWorldQA	27.6
CharXiv †	46.9
InfographicVQA †	70.0
Mind2Web †	36.8
Winoground	38.8
KIE (CORD+FUNSD) †	88.6
Moderation (Hateful Memes)	12.5
R-Bench-M	9.0
MMMU-Pro vision	5.3

Videos: Perception Test

Perception Test (validation)	d3-edge
All 19,140 questions	47.5
Memory	40.9
Abstraction	37.8
Physics	36.0
Semantics	71.5

Multiple-choice video question answering (three options per question, chance 33.3): top-1 accuracy (%), videos read with the defaults above.

_{d3-edge: internal evaluation. Others: live board data, text 2026-10-10, vision 2026-10-09.}

License

Apache-2.0 (LICENSE). Built on Qwen/Qwen3.5-0.8B (Apache-2.0).

Citation

@misc{d3_edge_2026,
  title        = {{d3-edge}: A Multimodal Foundation Decision Model},
  author       = {{vLLM Semantic Router Team}},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/vllm-sr/d3-edge}}
}

Trained on AMD Instinct MI325X GPUs.