Nvidia · Hugging Face
Multimodal open d1 decision models for the edge
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
These open d1 decision models are built on their Liquid Foundation Models (LFMs).
Key facts
- In collaboration with NVIDIA, they evaluated d1-3B on the NVIDIA stack across NVIDIA GeForce RTX 4090, NVIDIA Jetson AGX Thor, Jetson AGX Orin 64 GB, and Jetson Orin Nano
- The team validated that d1-3B retains the vision capabilities of its LFM2.5-VL-3B backbone on standard vision benchmarks, and that d1-omni-600M handles all three modalities
- On GPU, d1-3B answers a question in under 10 ms and processes a 384px image in under 18 ms on both platforms
- Edge inference. d1-3B answers a single question in under 50 ms on every measured device
Summary
Best decision model under 10B on the Decision Index 0.2.1: d1-3B scores 48.57, ahead of every 4B and 9B model and of Decider 35B-A3B (47.11). D1-3B is trained from LFM2.5-VL-3B, their latest VLM, which is decoder-only. D1-omni-600M is trained from LFM2.5-Encoder-350M, a bidirectional encoder. It accepts either text and image, or text and audio as inputs. The team benchmarked d1-3B and d1-omni-600M on seven public datasets spanning reading comprehension, toxicity detection, intent classification, medical QA, and cross-lingual understanding. d1-3B achieves a mean score of 82.9, the highest in the table and above Decider 4B. d1-omni-600M scores 78.4, surpassing Decider 2B (77.1) with only a quarter of the parameters.