cd /news/artificial-intelligence/decision-3-0-open-multimodal-sota-de… · home › topics › artificial-intelligence › article
[ARTICLE · art-149469] src=huggingface.co ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

Decision 3.0: open, multimodal SOTA decision models from 0.6B to 27B

Vllm-sr released the Decision 3.0 collection of open multimodal foundation decision models on Hugging Face, spanning six sizes from 0.6B to 26B parameters. The collection includes d3 (26B), d3-flash (8B), d3-mini (5B), d3-nano (2B), d3-lite (0.9B), and d3-edge (0.6B), all tagged for zero-shot classification and updated within about 24 hours of publication.

read1 min views1 publishedOct 12, 2026
Decision 3.0: open, multimodal SOTA decision models from 0.6B to 27B
Image: Hugging Face Blog

Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Website Tasks HuggingChat Collections Languages Organizations Community Blog Posts Daily Papers Hardware Learn Discord Forum GitHub Solutions Team & Enterprise Hugging Face PRO Enterprise Support Inference Providers Inference Endpoints Storage Buckets Log In Sign Up vllm-sr 's Collections 🔮Decision 3.0 ⛵ Vela 2.0 🧙 Decision 2.0 🎲 Decision 1.0 ⛵ Vela 1.0 🌊 MoM 1.0 🧙 MoM Nano 🔮Decision 3.0 updated 1 day ago Towards Open Multimodal Foundation Decision Models Upvote 55 +45 Sort: Collection vllm-sr/d3 Zero-Shot Classification • 26B • Updated 1 day ago • 130 • 45 vllm-sr/d3-flash Zero-Shot Classification • 8B • Updated 1 day ago • 69 • 27 vllm-sr/d3-mini Zero-Shot Classification • 5B • Updated 1 day ago • 62 • 9 vllm-sr/d3-nano Zero-Shot Classification • 2B • Updated 1 day ago • 82 • 9 vllm-sr/d3-lite Zero-Shot Classification • 0.9B • Updated 1 day ago • 83 • 8 vllm-sr/d3-edge Zero-Shot Classification • 0.6B • Updated about 24 hours ago • 33 • 19 Upvote 55 +51 Sort: Collection Share collection View history Collection guide Browse collections

source & further reading
huggingface.co — original article Open Source Engineering Challenge - HELP! It is not a hiding place. It is harm reduction What does a AI judge score of 0.8 actually mean? Introducing Typed Evals
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @hugging face 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/decision-3-0-open-mu…] indexed:0 read:1min 2026-10-12 · —