vLLM Semantic Router releases Decision 3.0 multimodal models with 5 sizes under Apache-2.0
vLLM Semantic Router has launched Decision 3.0, a family of open-source multimodal decision models that process text, JSON, and images to answer structured questions. The suite includes five model sizes—d3-lite (0.85B), d3-nano (2.21B), d3-mini (4.54B), d3-flash (8.39B), and d3 (26.09B)—all licensed under Apache-2.0. Unlike traditional LLMs, these models return probabilities for predefined…
Key points
- Five open-source Decision 3.0 models (0.85B–26.09B) support text, JSON, and images under Apache-2.0
- d3-flash (9B) outperforms Decision 2.0’s 27B model in text/vision benchmarks per internal evals
- Latency ranges from **21.7 ms** (text) to **342 ms** (with images) on AMD Instinct MI325X
The models are fine-tuned on Qwen checkpoints (Qwen3.5 for smaller sizes, Qwen3.8-27B for the largest) and include vision encoders for image input. Performance varies by task: the 27B model leads internal benchmarks (64.1 on text, 71.6 on vision), while the 9B d3-flash outperforms Decision 2.0’s 27B in both domains. Latency ranges from 21.7 ms (text-only) to 342 ms (with images) on a single AMD Instinct MI325X GPU. Scores on public benchmarks are mixed, with strengths in document extraction (97.7 on KIE) but weaker performance on moderation tasks (44.6 on Hateful Memes). All models are available on Hugging Face and GitHub, with installation notes specifying transformers==5.17.0 and optional optimizations.
What is Decision 3.0? vLLM Semantic Router’s New Open Decision Models
MarkTechPost · 11 October 2026
Loading the full article…
This text was published by MarkTechPost and written by Michal Sutter. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Microsoft releases Decision-1 AI model starting at $0.042 per million input tokens · 1 src
- Google launches Gemini 4 Argon model · 14 src
- Openbmb releases MiniCPM-V 4.7-35B-A3B, first open-source MoE model for on-device use · 2 src
- Jordan dismantles AI doom rhetoric as 'grand moralizing performance' · 1 src
- TypeSafe/Jev hits $100M ARR, $7.5B valuation three weeks after launch · 1 src
Comments
via GitHub Discussions