vLLM Semantic Router d3 27B
vLLM Semantic Router's 27B decision model on Qwen3.5: it reads a text or JSON state, or a still image, and answers choice, score and yes/no questions with probabilities.
d3 27B is an open-weight decision model built by vLLM Semantic Router. It reads a piece of text and answers typed questions about it, such as a choice between labels, a yes or no, or a score on a scale, with a probability for every option instead of written text. It runs entirely on your own hardware through Ollama: no API key and no per-use fees.
- Released
- Oct 2026
- Pricing
- Free, runs on your hardware
- Answers
- Choice, yes/no, score
vLLM Semantic Router
vLLM Semantic Router is the vLLM project's open decision layer for models and compute, and publishes the d3 decision models for routing, triage and scoring.
vllm-sr.ai ↗vLLM Semantic Router's 2B decision model on Qwen3.5: it reads a text or JSON state, or a still image, and answers choice, score and yes/no questions with probabilities.
vLLM Semantic Router's 4B decision model on Qwen3.5: it reads a text or JSON state, or a still image, and answers choice, score and yes/no questions with probabilities.
vLLM Semantic Router's 9B decision model on Qwen3.5: it reads a text or JSON state, or a still image, and answers choice, score and yes/no questions with probabilities.