Vllm Sr · Chat
d3-ultra
d3-ultra: 26B multimodal decision model (vLLM Semantic Router). Answers choice / yes-no / score / box / track questions about text, images and video with calibrated probabilities, without generating text.
Evidence and sources
🤗 vllm-sr/d3-ultraReleased 25 Oct 2026
Sources: NetMind.AI, llminfo researchPrimary data from NetMind.AI
from llminfo research: release date
Input & output
as stated by the model's providersText
Images
Text
Also known as: vllm-sr/d3-ultra
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works