What is Decision 3.0? vLLM Semantic Router’s New Open Decision Models
The vLLM Semantic Router team has released Decision 3.0, a family of multimodal decision models.
Proof1 independent outlet
Key points
- Decision 3.0 multimodal decision models read text, JSON and images, then answer typed questions about them.
- Size: 5 models: d3-lite (0.85B), d3-nano (2.21B), d3-mini (4.54B), d3-flash (8.39B), d3 (26.09B).
- BF16 weights; no official quantized variants listed.
- Best: 97.7 on KIE (CORD+FUNSD) document extraction (d3).
Sources (1)
- [1]What is Decision 3.0? vLLM Semantic Router’s New Open Decision ModelsMarkTechPost · Oct 11, 09:43 PM
The vLLM Semantic Router team has released Decision 3.0, a family of multimodal decision models.
Decision 3.0 multimodal decision models read text, JSON and images, then answer typed questions about them.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 11, 2026UPDATE: Qwen 3.8 27B 140 tok/s on single RTX 3090 Megakernel: KL divergence 0.0009 vs llama.cpp
- Oct 10, 2026[AINews] TypeSafe/Jev at >$100M ARR, $7.5B valuation 3 weeks after launch
- Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
- Oct 9, 2026Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 8, 2026ConwayResearch/Underdog-Saluki-27B-1.0
