AMD and vLLM team release open 27B multimodal decision model d3-ultra, #2 on Jev Decision Index
vllm_project · x · 2026-10-27
The vLLM Semantic Router team and AMD released d3-ultra, an open 27B multimodal decision model ranking #2 of 230 on the Jev Decision Index text board (+3.03 over d3). It handles text, images and video with per-answer probabilities, visual grounding (bounding boxes) and cross-frame video tracking. Apache-2.0 weights are on Hugging Face, trained and served on AMD Instinct GPUs, with xhigh/medium/low reasoning effort modes.
More from Models
- Open-weights chart shows xAI at 0% despite Musk's 2024 open-source pledge, DeepSeek at 100% — kingslyj · 2026-10-27
- Baidu's open-source Unlimited OCR tops 10M HuggingFace downloads, 28.3K GitHub stars — xiaohu · 2026-10-27
- Unlimited OCR 2 ingests 3,600-page Harry Potter in one go, cutting KV cache from 47GB to 1.77GB — xiaohu · 2026-10-27
- Models spontaneously run internal expert debates when solving hard problems, nobody designed it — profjamesevans · 2026-10-27
- Speculation: xAI's announcement is likely Index, not Fable 5.5 — ChrisGPT · 2026-10-27
- Reasoning is signed: building a universal LLM gateway hits encrypted CoT walls — respan-81 · 2026-10-27